vlad/reverse-skills-max
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

reverse-skills-max: initial public release (restored, redacted, hardened)

Browse Source
This commit is contained in:
baradok609hecl1pq6qi
2026-10-20 02:17:15 +03:00
commit da24c2bd20
2227 changed files with 443931 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

201
vendor-new/Anthropic-Cybersecurity-Skills/skills/performing-malware-ioc-extraction/LICENSE Normal file
View File

@@ -0,0 +1,201 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to the Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by the Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding any notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. Please do not remove or change
the license header comment from a contributed file except when
necessary.
Copyright 2026 mukul975
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

376
vendor-new/Anthropic-Cybersecurity-Skills/skills/performing-malware-ioc-extraction/SKILL.md Normal file
View File

@@ -0,0 +1,376 @@
---
name: performing-malware-ioc-extraction
description: Malware IOC extraction is the process of analyzing malicious software
to identify actionable indicators of compromise including file hashes, network indicators
(C2 domains, IP addresses, URLs), regist
domain: cybersecurity
subdomain: threat-intelligence
tags:
- threat-intelligence
- cti
- ioc
- mitre-attack
- stix
- malware-analysis
- yara
- reverse-engineering
version: '1.0'
author: mahipal
license: Apache-2.0
nist_csf:
- ID.RA-01
- ID.RA-05
- DE.CM-01
- DE.AE-02
mitre_attack:
- T1591
- T1592
- T1593
- T1589
- T1071
---
# Performing Malware IOC Extraction
## Overview
Malware IOC extraction is the process of analyzing malicious software to identify actionable indicators of compromise including file hashes, network indicators (C2 domains, IP addresses, URLs), registry modifications, mutex names, embedded strings, and behavioral artifacts. This skill covers static analysis with PE parsing and string extraction, dynamic analysis with sandbox detonation, automated IOC extraction using tools like YARA, and formatting results as STIX 2.1 indicators for sharing.
## When to Use
- When conducting security assessments that involve performing malware ioc extraction
- When following incident response procedures for related security events
- When performing scheduled security testing or auditing activities
- When validating security controls through hands-on testing
## Prerequisites
- Python 3.9+ with `pefile`, `yara-python`, `oletools`, `stix2` libraries
- Access to malware analysis sandbox (Cuckoo, CAPE, Any.Run, Joe Sandbox)
- VirusTotal API key for enrichment
- Isolated analysis environment (VM or container)
- Understanding of PE file format, common packing techniques
- Familiarity with YARA rule syntax
## Key Concepts
### Static Analysis IOCs
- **File Hashes**: MD5, SHA-1, SHA-256 of the sample and any dropped files
- **Import Hash (imphash)**: Hash of imported function table, groups malware families
- **Rich Header Hash**: PE rich header hash for compiler fingerprinting
- **Strings**: Embedded URLs, IP addresses, domain names, registry paths, mutex names
- **PE Metadata**: Compilation timestamp, section names, resources, digital signatures
- **Embedded Artifacts**: PDB paths, version info, certificate details
### Dynamic Analysis IOCs
- **Network Activity**: DNS queries, HTTP requests, TCP/UDP connections, SSL certificates
- **File System**: Created/modified/deleted files and directories
- **Registry**: Created/modified registry keys and values
- **Process**: Spawned processes, injected processes, service creation
- **Behavioral**: API calls, mutex creation, scheduled tasks, persistence mechanisms
### YARA Rules
YARA is a pattern-matching tool for identifying and classifying malware. Rules consist of strings (text, hex, regex) and conditions that define matching logic. Rules can detect malware families, packers, exploit kits, and specific campaign tools.
## Workflow
### Step 1: Static Analysis - PE Parsing and Hash Generation
```python
import pefile
import hashlib
import os
def analyze_pe(filepath):
"""Extract IOCs from a PE file through static analysis."""
iocs = {"hashes": {}, "pe_info": {}, "strings": [], "imports": []}
# Calculate file hashes
with open(filepath, "rb") as f:
data = f.read()
iocs["hashes"]["md5"] = hashlib.md5(data).hexdigest()
iocs["hashes"]["sha1"] = hashlib.sha1(data).hexdigest()
iocs["hashes"]["sha256"] = hashlib.sha256(data).hexdigest()
iocs["hashes"]["file_size"] = len(data)
# Parse PE headers
try:
pe = pefile.PE(filepath)
iocs["hashes"]["imphash"] = pe.get_imphash()
iocs["pe_info"]["compilation_time"] = str(pe.FILE_HEADER.TimeDateStamp)
iocs["pe_info"]["machine_type"] = hex(pe.FILE_HEADER.Machine)
iocs["pe_info"]["subsystem"] = pe.OPTIONAL_HEADER.Subsystem
# Extract sections
iocs["pe_info"]["sections"] = []
for section in pe.sections:
iocs["pe_info"]["sections"].append({
"name": section.Name.decode("utf-8", errors="ignore").strip("\x00"),
"virtual_size": section.Misc_VirtualSize,
"raw_size": section.SizeOfRawData,
"entropy": section.get_entropy(),
"md5": section.get_hash_md5(),
})
# Extract imports
if hasattr(pe, "DIRECTORY_ENTRY_IMPORT"):
for entry in pe.DIRECTORY_ENTRY_IMPORT:
dll_name = entry.dll.decode("utf-8", errors="ignore")
functions = [
imp.name.decode("utf-8", errors="ignore")
for imp in entry.imports
if imp.name
]
iocs["imports"].append({"dll": dll_name, "functions": functions})
# Check for suspicious characteristics
iocs["pe_info"]["is_dll"] = pe.is_dll()
iocs["pe_info"]["is_driver"] = pe.is_driver()
iocs["pe_info"]["is_exe"] = pe.is_exe()
# Version info
if hasattr(pe, "VS_VERSIONINFO"):
for entry in pe.FileInfo:
for st in entry:
for item in st.entries.items():
key = item[0].decode("utf-8", errors="ignore")
val = item[1].decode("utf-8", errors="ignore")
iocs["pe_info"][f"version_{key}"] = val
pe.close()
except pefile.PEFormatError as e:
iocs["pe_info"]["error"] = str(e)
return iocs
```
### Step 2: String Extraction and IOC Pattern Matching
```python
import re
def extract_ioc_strings(filepath):
"""Extract IOC-relevant strings from binary file."""
patterns = {
"ipv4": re.compile(
r"\b(?:(?:25[0-5]|2[0-4]\d|[01]?\d\d?)\.){3}"
r"(?:25[0-5]|2[0-4]\d|[01]?\d\d?)\b"
),
"domain": re.compile(
r"\b(?:[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?\.)+"
r"(?:com|net|org|io|ru|cn|tk|xyz|top|info|biz|cc|ws|pw)\b"
),
"url": re.compile(
r"https?://[^\s\"'<>]{5,200}"
),
"email": re.compile(
r"\b[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}\b"
),
"registry": re.compile(
r"(?:HKEY_[A-Z_]+|HKLM|HKCU|HKU|HKCR|HKCC)"
r"\\[\\a-zA-Z0-9_ .{}-]+"
),
"filepath_windows": re.compile(
r"[A-Z]:\\(?:[^\\/:*?\"<>|\r\n]+\\)*[^\\/:*?\"<>|\r\n]+"
),
"mutex": re.compile(
r"(?:Global\\|Local\\)[a-zA-Z0-9_\-{}.]{4,}"
),
"useragent": re.compile(
r"Mozilla/[45]\.0[^\"']{10,200}"
),
"bitcoin": re.compile(
r"\b[13][a-km-zA-HJ-NP-Z1-9]{25,34}\b"
),
"pdb_path": re.compile(
r"[A-Z]:\\[^\"]{5,200}\.pdb"
),
}
with open(filepath, "rb") as f:
data = f.read()
# Extract ASCII strings (min length 4)
ascii_strings = re.findall(rb"[\x20-\x7e]{4,}", data)
# Extract Unicode strings
unicode_strings = re.findall(
rb"(?:[\x20-\x7e]\x00){4,}", data
)
all_strings = [s.decode("ascii", errors="ignore") for s in ascii_strings]
all_strings += [
s.decode("utf-16-le", errors="ignore") for s in unicode_strings
]
extracted = {category: set() for category in patterns}
for string in all_strings:
for category, pattern in patterns.items():
matches = pattern.findall(string)
for match in matches:
extracted[category].add(match)
# Convert sets to sorted lists
return {k: sorted(v) for k, v in extracted.items() if v}
```
### Step 3: YARA Rule Scanning
```python
import yara
def scan_with_yara(filepath, rules_path):
"""Scan file with YARA rules for malware classification."""
rules = yara.compile(filepath=rules_path)
matches = rules.match(filepath)
results = []
for match in matches:
result = {
"rule": match.rule,
"namespace": match.namespace,
"tags": match.tags,
"meta": match.meta,
"strings": [],
}
for offset, identifier, data in match.strings:
result["strings"].append({
"offset": hex(offset),
"identifier": identifier,
"data": data.hex() if len(data) < 100 else data[:100].hex() + "...",
})
results.append(result)
return results
# Example YARA rule for common malware indicators
SAMPLE_YARA_RULE = """
rule Suspicious_Network_Indicators {
meta:
description = "Detects suspicious network-related strings"
author = "CTI Analyst"
severity = "medium"
strings:
$ua1 = "Mozilla/5.0" ascii
$cmd1 = "cmd.exe /c" ascii nocase
$ps1 = "powershell" ascii nocase
$wget = "wget" ascii nocase
$curl = "curl" ascii nocase
$b64 = "base64" ascii nocase
$reg1 = "HKLM\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Run" ascii nocase
condition:
uint16(0) == 0x5A4D and
(2 of ($ua1, $cmd1, $ps1, $wget, $curl, $b64)) or $reg1
}
rule Packed_Binary {
meta:
description = "Detects potentially packed binary"
author = "CTI Analyst"
condition:
uint16(0) == 0x5A4D and
for any section in pe.sections : (
section.entropy >= 7.0
)
}
"""
```
### Step 4: Generate STIX 2.1 Indicators
```python
from stix2 import (
Bundle, Indicator, Malware, Relationship,
File as STIXFile, DomainName, IPv4Address,
ObservedData,
)
from datetime import datetime
def create_stix_bundle(pe_iocs, string_iocs, yara_results, sample_name):
"""Create STIX 2.1 bundle from extracted IOCs."""
objects = []
# Create Malware SDO
malware = Malware(
name=sample_name,
is_family=False,
malware_types=["unknown"],
description=f"Malware sample analyzed: {pe_iocs['hashes']['sha256']}",
allow_custom=True,
)
objects.append(malware)
# File hash indicator
sha256 = pe_iocs["hashes"]["sha256"]
hash_indicator = Indicator(
name=f"Malware hash: {sha256[:16]}...",
pattern=f"[file:hashes.'SHA-256' = '{sha256}']",
pattern_type="stix",
valid_from=datetime.now().strftime("%Y-%m-%dT%H:%M:%SZ"),
indicator_types=["malicious-activity"],
allow_custom=True,
)
objects.append(hash_indicator)
objects.append(Relationship(
relationship_type="indicates",
source_ref=hash_indicator.id,
target_ref=malware.id,
))
# Network indicators from strings
for ip in string_iocs.get("ipv4", []):
if not ip.startswith(("10.", "172.", "192.168.", "127.")):
ip_indicator = Indicator(
name=f"C2 IP: {ip}",
pattern=f"[ipv4-addr:value = '{ip}']",
pattern_type="stix",
valid_from=datetime.now().strftime("%Y-%m-%dT%H:%M:%SZ"),
indicator_types=["malicious-activity"],
allow_custom=True,
)
objects.append(ip_indicator)
objects.append(Relationship(
relationship_type="indicates",
source_ref=ip_indicator.id,
target_ref=malware.id,
))
for domain in string_iocs.get("domain", []):
domain_indicator = Indicator(
name=f"C2 Domain: {domain}",
pattern=f"[domain-name:value = '{domain}']",
pattern_type="stix",
valid_from=datetime.now().strftime("%Y-%m-%dT%H:%M:%SZ"),
indicator_types=["malicious-activity"],
allow_custom=True,
)
objects.append(domain_indicator)
objects.append(Relationship(
relationship_type="indicates",
source_ref=domain_indicator.id,
target_ref=malware.id,
))
bundle = Bundle(objects=objects, allow_custom=True)
return bundle
```
## Validation Criteria
- PE file parsed successfully with hashes, imports, and section analysis
- String extraction identifies network IOCs (IPs, domains, URLs)
- YARA rules match against known malware characteristics
- STIX 2.1 bundle contains valid Indicator and Malware objects
- Private IP ranges and benign strings filtered from IOC output
- IOCs are actionable for blocking and detection rule creation
## References
- [pefile Documentation](https://github.com/erocarrera/pefile)
- [YARA Documentation](https://yara.readthedocs.io/)
- [MITRE ATT&CK Software](https://attack.mitre.org/software/)
- [VirusTotal API](https://docs.virustotal.com/)
- [CAPE Sandbox](https://github.com/kevoreilly/CAPEv2)
- [MalwareBazaar](https://bazaar.abuse.ch/)

99
vendor-new/Anthropic-Cybersecurity-Skills/skills/performing-malware-ioc-extraction/assets/template.md Normal file
View File

@@ -0,0 +1,99 @@
# Malware IOC Extraction Report Template
## Sample Information
| Field | Value |
|-------|-------|
| Filename | |
| File Size | |
| File Type | PE32/PE32+/ELF/Mach-O |
| MD5 | |
| SHA-1 | |
| SHA-256 | |
| Imphash | |
| SSDeep | |
| First Seen | |
## PE Analysis
| Attribute | Value |
|-----------|-------|
| Compile Time | |
| Entry Point | |
| Machine Type | |
| Subsystem | |
| Is DLL | |
| Digital Signature | Valid/Invalid/None |
### Sections
| Name | Virtual Size | Raw Size | Entropy | Suspicious |
|------|-------------|----------|---------|------------|
| .text | | | | |
| .data | | | | |
| .rsrc | | | | |
### Suspicious API Imports
| DLL | Function | Purpose |
|-----|----------|---------|
| kernel32.dll | VirtualAlloc | Memory allocation (code injection) |
| kernel32.dll | CreateRemoteThread | Process injection |
| wininet.dll | InternetOpenA | Network communication |
## Network IOCs
### IP Addresses
| IP | Context | Confidence |
|----|---------|-----------|
| | C2 Server | High/Med/Low |
### Domains
| Domain | Context | Confidence |
|--------|---------|-----------|
| | C2 Domain | High/Med/Low |
### URLs
| URL | Context | Confidence |
|-----|---------|-----------|
| | Payload Download | High/Med/Low |
## Host IOCs
### Registry Keys
| Key Path | Value | Purpose |
|----------|-------|---------|
| HKLM\...\Run | | Persistence |
### Mutexes
| Mutex Name | Purpose |
|-----------|---------|
| | Infection marker |
### File System Artifacts
| Path | Description |
|------|------------|
| | Dropped payload |
## YARA Matches
| Rule | Tags | Description |
|------|------|------------|
| | | |
## VirusTotal Results
| Metric | Value |
|--------|-------|
| Detection Ratio | X / Y |
| Threat Label | |
| First Submission | |
| Community Score | |
## MITRE ATT&CK Mapping
| Technique | Name | Evidence |
|-----------|------|----------|
| T1059.001 | PowerShell | Embedded PS commands |
| T1547.001 | Registry Run Keys | HKLM Run key modification |
| T1071.001 | Web Protocols | HTTP C2 communication |
## Recommendations
1. **Block**: Add network IOCs to firewall/proxy blocklists
2. **Detect**: Deploy YARA rules on endpoints and email gateways
3. **Hunt**: Search for host IOCs across the environment
4. **Share**: Upload IOCs to MISP with TLP classification

48
vendor-new/Anthropic-Cybersecurity-Skills/skills/performing-malware-ioc-extraction/references/api-reference.md Normal file
View File

@@ -0,0 +1,48 @@
# API Reference — Performing Malware IOC Extraction
## Libraries Used
- **re**: Regex patterns for 16 IOC types including defanged indicators
- **hashlib**: MD5, SHA1, SHA256 file hashing
- **pathlib**: File reading (text and binary)
## CLI Interface
```
python agent.py text --file threat_report.txt
python agent.py hash --file malware.exe
python agent.py strings --file malware.exe [--min-length 6]
python agent.py report --file malware.exe [--output iocs.json]
```
## Core Functions
### `extract_iocs_from_text(text)` — Extract IOCs with defanging support
Handles defanged indicators: `[.]` -> `.`, `hxxp` -> `http`. Filters private IPs.
### `extract_from_file(file_path)` — Extract IOCs from text/report files
### `hash_file(file_path)` — Calculate MD5/SHA1/SHA256 hashes
### `extract_strings(file_path, min_length)` — Binary string extraction
Extracts ASCII and wide (UTF-16LE) strings. Identifies suspicious API calls and keywords.
### `generate_ioc_report(file_path, output)` — Full analysis report
## IOC Pattern Types (16)
| Type | Example |
|------|---------|
| ipv4 | 192.168.1.1 (private filtered) |
| domain | evil.example.com |
| url | https://malware.example.com/payload |
| md5/sha1/sha256 | File hashes |
| cve | CVE-2024-12345 |
| registry_key | HKLM\Software\... |
| file_path_windows | C:\Windows\Temp\mal.exe |
| mutex | Global\MutexName |
| mitre_technique | T1059.001 |
| bitcoin_addr | Bitcoin wallet address |
| user_agent | Mozilla/5.0 strings |
## Suspicious String Keywords
CreateRemoteThread, VirtualAlloc, WriteProcessMemory, LoadLibrary,
GetProcAddress, WinExec, ShellExecute, powershell, cmd.exe
## Dependencies
No external packages — Python standard library only.

81
vendor-new/Anthropic-Cybersecurity-Skills/skills/performing-malware-ioc-extraction/references/standards.md Normal file
View File

@@ -0,0 +1,81 @@
# Standards and Frameworks Reference
## IOC Types and Classification
### File-Based IOCs
| Type | Description | Example |
|------|-------------|---------|
| MD5 | 128-bit hash | d41d8cd98f00b204e9800998ecf8427e |
| SHA-1 | 160-bit hash | da39a3ee5e6b4b0d3255bfef95601890afd80709 |
| SHA-256 | 256-bit hash | e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855 |
| Imphash | Import hash | PE import table hash for family grouping |
| SSDeep | Fuzzy hash | Context-triggered piecewise hash for similarity |
| TLSH | Trend Micro LSH | Locality-sensitive hash for near-duplicate detection |
### Network IOCs
| Type | Description | Example |
|------|-------------|---------|
| IPv4 Address | C2 server IP | 192.0.2.1 |
| Domain | C2 domain | malware-c2.example.com |
| URL | Full URL path | https://evil.com/payload.exe |
| JA3/JA3S | TLS fingerprint | Client/server TLS handshake hash |
| JARM | TLS server fingerprint | Active TLS server scanning fingerprint |
| User-Agent | HTTP User-Agent | Custom UA strings in beacons |
### Host-Based IOCs
| Type | Description | Example |
|------|-------------|---------|
| Mutex | Named mutex | Global\{GUID} |
| Registry Key | Registry modification | HKLM\SOFTWARE\...\Run |
| Scheduled Task | Persistence task | schtasks /create ... |
| Service Name | Malicious service | Malicious service installation |
| Named Pipe | IPC mechanism | \\.\pipe\name |
| PDB Path | Debug path | C:\Users\dev\project.pdb |
## STIX 2.1 Indicator Patterns
### Pattern Syntax
```
[file:hashes.'SHA-256' = 'abc123...']
[ipv4-addr:value = '1.2.3.4']
[domain-name:value = 'evil.com']
[url:value = 'https://evil.com/payload']
[file:name = 'malware.exe']
[email-addr:value = 'attacker@evil.com']
[network-traffic:dst_ref.type = 'ipv4-addr' AND network-traffic:dst_port = 443]
```
## YARA Rule Structure
```
rule RuleName {
meta:
author = "Analyst"
description = "Detection rule"
reference = "URL"
date = "YYYY-MM-DD"
hash = "SHA256"
tlp = "white"
strings:
$text = "string" ascii wide nocase
$hex = { 4D 5A 90 00 }
$regex = /pattern[0-9]+/
condition:
uint16(0) == 0x5A4D and filesize < 5MB and any of them
}
```
## PE File Format
- **DOS Header**: MZ signature (0x5A4D)
- **PE Header**: PE signature, machine type, timestamp
- **Optional Header**: Entry point, image base, subsystem
- **Section Table**: .text, .data, .rdata, .rsrc, .reloc
- **Import Table**: DLLs and functions used
- **Export Table**: Functions exported (DLLs)
- **Resource Table**: Embedded resources (icons, strings, configs)
## References
- [STIX 2.1 Patterning](https://docs.oasis-open.org/cti/stix/v2.1/os/stix-v2.1-os.html#_e8slinrhxcc9)
- [YARA Documentation](https://yara.readthedocs.io/en/stable/)
- [PE Format Specification](https://learn.microsoft.com/en-us/windows/win32/debug/pe-format)
- [MalwareBazaar Database](https://bazaar.abuse.ch/)

70
vendor-new/Anthropic-Cybersecurity-Skills/skills/performing-malware-ioc-extraction/references/workflows.md Normal file
View File

@@ -0,0 +1,70 @@
# Malware IOC Extraction Workflows
## Workflow 1: Static Analysis Pipeline
```
[Malware Sample] --> [Hash Generation] --> [PE Parsing] --> [String Extraction] --> [IOC Filtering]
|
v
[YARA Scanning]
|
v
[STIX Bundle]
```
### Steps:
1. **Sample Acquisition**: Obtain sample from MalwareBazaar, VirusTotal, or incident response
2. **Hash Calculation**: Generate MD5, SHA-1, SHA-256, imphash, ssdeep hashes
3. **PE Analysis**: Parse headers, sections, imports, exports, resources, timestamps
4. **String Extraction**: Extract ASCII/Unicode strings, apply IOC regex patterns
5. **IOC Filtering**: Remove false positives (private IPs, common DLLs, benign domains)
6. **YARA Classification**: Scan with community and custom YARA rules
7. **Output**: Generate STIX 2.1 bundle with extracted indicators
## Workflow 2: Dynamic Analysis Pipeline
```
[Malware Sample] --> [Sandbox Submission] --> [Detonation] --> [Artifact Collection]
|
+------------+------------+
| | |
v v v
[Network] [File Sys] [Registry]
[PCAPs] [Changes] [Changes]
| | |
+------------+------------+
|
v
[IOC Consolidation]
```
### Steps:
1. **Sandbox Setup**: Configure isolated VM with network monitoring
2. **Sample Submission**: Submit to CAPE/Cuckoo sandbox with execution parameters
3. **Execution Monitoring**: Monitor for 3-5 minutes of runtime behavior
4. **Network Capture**: Extract DNS queries, HTTP/HTTPS traffic, raw connections
5. **File System Analysis**: Identify created, modified, and deleted files
6. **Registry Analysis**: Capture registry key changes for persistence indicators
7. **Process Analysis**: Document spawned processes, injections, privilege escalation
8. **Consolidation**: Merge static and dynamic IOCs into unified report
## Workflow 3: Automated IOC Pipeline
```
[Feed/Alert] --> [Auto-Download] --> [Static Analysis] --> [Sandbox] --> [Enrichment] --> [Share]
|
v
[VirusTotal Check]
|
v
[MISP/OpenCTI Upload]
```
### Steps:
1. **Trigger**: New sample from malware feed, email gateway, or EDR alert
2. **Download**: Retrieve sample securely to analysis infrastructure
3. **Static Scan**: Automated PE parsing, string extraction, YARA scanning
4. **Dynamic Analysis**: Submit to sandbox for behavioral analysis
5. **Enrichment**: Check hashes against VirusTotal, cross-reference with TI platforms
6. **Deduplication**: Remove already-known IOCs from output
7. **Sharing**: Upload new IOCs to MISP/OpenCTI for team consumption

150
vendor-new/Anthropic-Cybersecurity-Skills/skills/performing-malware-ioc-extraction/scripts/agent.py Normal file
View File

@@ -0,0 +1,150 @@
#!/usr/bin/env python3
"""Agent for performing malware IOC extraction from files, reports, and samples."""
import json
import argparse
import re
import hashlib
from datetime import datetime, timezone
from pathlib import Path
IOC_PATTERNS = {
"ipv4": re.compile(r"\b(?:(?:25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)\.){3}(?:25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)\b"),
"ipv6": re.compile(r"\b(?:[0-9a-fA-F]{1,4}:){7}[0-9a-fA-F]{1,4}\b"),
"domain": re.compile(r"\b(?:[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?\.)+(?:com|net|org|io|ru|cn|xyz|top|info|biz|cc|tk|ml|ga|cf|gq|pw)\b"),
"url": re.compile(r"https?://[^\s<>\"'\)]+"),
"email": re.compile(r"\b[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}\b"),
"md5": re.compile(r"\b[a-f0-9]{32}\b"),
"sha1": re.compile(r"\b[a-f0-9]{40}\b"),
"sha256": re.compile(r"\b[a-f0-9]{64}\b"),
"cve": re.compile(r"CVE-\d{4}-\d{4,7}", re.I),
"registry_key": re.compile(r"(?:HKLM|HKCU|HKCR|HKU|HKCC)\\[^\s\"']+"),
"file_path_windows": re.compile(r"[A-Z]:\\(?:[^\s\\\"]+\\)*[^\s\\\"]+\.\w{1,5}"),
"file_path_unix": re.compile(r"/(?:tmp|var|etc|usr|home|opt|bin|sbin)/[^\s\"']+"),
"mutex": re.compile(r"(?:Global|Local)\\[^\s\"']+"),
"bitcoin_addr": re.compile(r"\b[13][a-km-zA-HJ-NP-Z1-9]{25,34}\b"),
"mitre_technique": re.compile(r"T\d{4}(?:\.\d{3})?"),
"user_agent": re.compile(r"Mozilla/5\.0[^\n\"]{20,200}"),
}
DEFANGED_PATTERNS = {
"ip_defanged": (re.compile(r"\b\d+\[\.\]\d+\[\.\]\d+\[\.\]\d+\b"), lambda m: m.group().replace("[.]", ".")),
"url_defanged": (re.compile(r"hxxps?://[^\s]+"), lambda m: m.group().replace("hxxp", "http")),
"domain_defanged": (re.compile(r"\b\S+\[\.\]\S+\b"), lambda m: m.group().replace("[.]", ".")),
}
def extract_iocs_from_text(text):
"""Extract all IOC types from raw text."""
refanged = text
for name, (pattern, fixer) in DEFANGED_PATTERNS.items():
refanged = pattern.sub(fixer, refanged)
extracted = {}
for ioc_type, pattern in IOC_PATTERNS.items():
matches = list(set(pattern.findall(refanged)))
if matches:
extracted[ioc_type] = sorted(matches)[:200]
private_ip = re.compile(r"^(?:10\.|172\.(?:1[6-9]|2\d|3[01])\.|192\.168\.|127\.)")
if "ipv4" in extracted:
extracted["ipv4"] = [ip for ip in extracted["ipv4"] if not private_ip.match(ip)]
return extracted
def extract_from_file(file_path):
"""Extract IOCs from a file (text, PDF text, or report)."""
content = Path(file_path).read_text(encoding="utf-8", errors="replace")
iocs = extract_iocs_from_text(content)
total = sum(len(v) for v in iocs.values())
return {
"source": file_path, "total_iocs": total,
"by_type": {k: len(v) for k, v in iocs.items()},
"indicators": iocs,
}
def hash_file(file_path):
"""Calculate file hashes for malware sample identification."""
data = Path(file_path).read_bytes()
return {
"file": file_path,
"size_bytes": len(data),
"md5": hashlib.md5(data).hexdigest(),
"sha1": hashlib.sha1(data).hexdigest(),
"sha256": hashlib.sha256(data).hexdigest(),
}
def extract_strings(file_path, min_length=6):
"""Extract printable strings from binary file."""
data = Path(file_path).read_bytes()
ascii_strings = re.findall(rb"[\x20-\x7e]{%d,}" % min_length, data)
wide_strings = re.findall(rb"(?:[\x20-\x7e]\x00){%d,}" % min_length, data)
all_strings = [s.decode("ascii", errors="replace") for s in ascii_strings]
all_strings += [s.decode("utf-16-le", errors="replace") for s in wide_strings]
iocs = extract_iocs_from_text("\n".join(all_strings))
suspicious = []
suspicious_kw = ["http", "socket", "connect", "download", "upload", "exec", "cmd.exe",
"powershell", "reg add", "CreateRemoteThread", "VirtualAlloc", "WriteProcessMemory",
"LoadLibrary", "GetProcAddress", "WinExec", "ShellExecute"]
for s in all_strings:
if any(kw.lower() in s.lower() for kw in suspicious_kw):
suspicious.append(s[:200])
return {
"file": file_path, "total_strings": len(all_strings),
"suspicious_strings": suspicious[:30],
"extracted_iocs": {k: len(v) for k, v in iocs.items()},
"ioc_details": iocs,
}
def generate_ioc_report(file_path, output=None):
"""Generate comprehensive IOC extraction report."""
hashes = hash_file(file_path)
strings = extract_strings(file_path)
report = {
"generated": datetime.now(timezone.utc).isoformat(),
"file_info": hashes,
"strings_analysis": {
"total": strings["total_strings"],
"suspicious": strings["suspicious_strings"],
},
"extracted_iocs": strings["ioc_details"],
"ioc_summary": strings["extracted_iocs"],
}
if output:
with open(output, "w") as f:
json.dump(report, f, indent=2)
return report
def main():
parser = argparse.ArgumentParser(description="Malware IOC Extraction Agent")
sub = parser.add_subparsers(dest="command")
t = sub.add_parser("text", help="Extract IOCs from text/report file")
t.add_argument("--file", required=True)
h = sub.add_parser("hash", help="Calculate file hashes")
h.add_argument("--file", required=True)
s = sub.add_parser("strings", help="Extract strings and IOCs from binary")
s.add_argument("--file", required=True)
s.add_argument("--min-length", type=int, default=6)
r = sub.add_parser("report", help="Generate full IOC report")
r.add_argument("--file", required=True)
r.add_argument("--output", help="Output JSON file")
args = parser.parse_args()
if args.command == "text":
result = extract_from_file(args.file)
elif args.command == "hash":
result = hash_file(args.file)
elif args.command == "strings":
result = extract_strings(args.file, args.min_length)
elif args.command == "report":
result = generate_ioc_report(args.file, args.output)
else:
parser.print_help()
return
print(json.dumps(result, indent=2, default=str))
if __name__ == "__main__":
main()

452
vendor-new/Anthropic-Cybersecurity-Skills/skills/performing-malware-ioc-extraction/scripts/process.py Normal file
View File

@@ -0,0 +1,452 @@
#!/usr/bin/env python3
"""
Malware IOC Extraction Script
Performs static analysis on PE files to extract IOCs:
- File hash generation (MD5, SHA-1, SHA-256, imphash)
- PE header parsing and section analysis
- String extraction with IOC pattern matching
- YARA rule scanning
- STIX 2.1 bundle generation
Requirements:
pip install pefile yara-python stix2 requests
Usage:
python process.py --file malware.exe --output iocs.json
python process.py --file malware.exe --yara-rules rules/ --stix-output bundle.json
python process.py --file malware.exe --vt-check --vt-key YOUR_KEY
"""
import argparse
import hashlib
import json
import os
import re
import sys
from datetime import datetime
from typing import Optional
try:
import pefile
except ImportError:
pefile = None
try:
import yara
except ImportError:
yara = None
class MalwareIOCExtractor:
"""Extract IOCs from malware samples via static analysis."""
def __init__(self, filepath: str):
self.filepath = filepath
self.filename = os.path.basename(filepath)
with open(filepath, "rb") as f:
self.data = f.read()
self.hashes = self._calculate_hashes()
self.iocs = {
"file": {"name": self.filename, "size": len(self.data)},
"hashes": self.hashes,
"pe_info": {},
"network_iocs": {},
"host_iocs": {},
"yara_matches": [],
"suspicious_strings": [],
}
def _calculate_hashes(self) -> dict:
return {
"md5": hashlib.md5(self.data).hexdigest(),
"sha1": hashlib.sha1(self.data).hexdigest(),
"sha256": hashlib.sha256(self.data).hexdigest(),
}
def analyze_pe(self):
"""Parse PE file structure and extract metadata IOCs."""
if pefile is None:
print("[-] pefile not installed, skipping PE analysis")
return
try:
pe = pefile.PE(data=self.data)
except pefile.PEFormatError:
print("[-] Not a valid PE file")
return
self.iocs["hashes"]["imphash"] = pe.get_imphash()
# Compilation timestamp
timestamp = pe.FILE_HEADER.TimeDateStamp
try:
compile_time = datetime.utcfromtimestamp(timestamp).isoformat()
except (OSError, ValueError):
compile_time = f"invalid ({timestamp})"
self.iocs["pe_info"] = {
"compile_time": compile_time,
"machine": hex(pe.FILE_HEADER.Machine),
"is_dll": pe.is_dll(),
"is_exe": pe.is_exe(),
"entry_point": hex(pe.OPTIONAL_HEADER.AddressOfEntryPoint),
"image_base": hex(pe.OPTIONAL_HEADER.ImageBase),
"sections": [],
"imports": [],
"exports": [],
}
# Section analysis
for section in pe.sections:
name = section.Name.decode("utf-8", errors="ignore").strip("\x00")
entropy = section.get_entropy()
self.iocs["pe_info"]["sections"].append({
"name": name,
"virtual_size": section.Misc_VirtualSize,
"raw_size": section.SizeOfRawData,
"entropy": round(entropy, 2),
"suspicious": entropy > 7.0,
"md5": hashlib.md5(section.get_data()).hexdigest(),
})
# Import table
if hasattr(pe, "DIRECTORY_ENTRY_IMPORT"):
for entry in pe.DIRECTORY_ENTRY_IMPORT:
dll = entry.dll.decode("utf-8", errors="ignore")
funcs = []
for imp in entry.imports:
if imp.name:
funcs.append(imp.name.decode("utf-8", errors="ignore"))
self.iocs["pe_info"]["imports"].append({
"dll": dll,
"functions": funcs,
})
# Suspicious API imports
suspicious_apis = {
"VirtualAlloc", "VirtualProtect", "CreateRemoteThread",
"WriteProcessMemory", "NtUnmapViewOfSection", "IsDebuggerPresent",
"GetProcAddress", "LoadLibraryA", "LoadLibraryW",
"URLDownloadToFileA", "InternetOpenA", "HttpSendRequestA",
"WinExec", "ShellExecuteA", "CreateProcessA",
"RegSetValueExA", "CryptEncrypt", "CryptDecrypt",
}
found_suspicious = set()
for imp_entry in self.iocs["pe_info"]["imports"]:
for func in imp_entry["functions"]:
if func in suspicious_apis:
found_suspicious.add(func)
self.iocs["pe_info"]["suspicious_apis"] = sorted(found_suspicious)
# Export table
if hasattr(pe, "DIRECTORY_ENTRY_EXPORT"):
for exp in pe.DIRECTORY_ENTRY_EXPORT.symbols:
if exp.name:
self.iocs["pe_info"]["exports"].append(
exp.name.decode("utf-8", errors="ignore")
)
pe.close()
def extract_strings(self, min_length: int = 4):
"""Extract and classify strings from the binary."""
patterns = {
"ipv4": re.compile(
r"\b(?:(?:25[0-5]|2[0-4]\d|[01]?\d\d?)\.){3}"
r"(?:25[0-5]|2[0-4]\d|[01]?\d\d?)\b"
),
"domain": re.compile(
r"\b(?:[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?\.)+"
r"(?:com|net|org|io|ru|cn|tk|xyz|top|info|biz|cc|ws|pw|"
r"onion|bit|me|co|uk|de|fr|jp|kr|br)\b"
),
"url": re.compile(r"https?://[^\s\"'<>\x00]{5,200}"),
"email": re.compile(
r"\b[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}\b"
),
"registry": re.compile(
r"(?:HKEY_[A-Z_]+|HKLM|HKCU|HKU|HKCR)"
r"\\[\\a-zA-Z0-9_ .{}\-]+"
),
"filepath": re.compile(
r"[A-Z]:\\(?:[^\\/:*?\"<>|\r\n\x00]+\\)*[^\\/:*?\"<>|\r\n\x00]+"
),
"mutex": re.compile(r"(?:Global\\|Local\\)[a-zA-Z0-9_\-{}.]{4,}"),
"useragent": re.compile(r"Mozilla/[45]\.0[^\"'\x00]{10,200}"),
"pdb_path": re.compile(r"[A-Z]:\\[^\x00\"]{5,200}\.pdb"),
"bitcoin_wallet": re.compile(
r"\b[13][a-km-zA-HJ-NP-Z1-9]{25,34}\b"
),
}
# Extract ASCII strings
ascii_regex = re.compile(rb"[\x20-\x7e]{%d,}" % min_length)
ascii_strings = [
s.decode("ascii", errors="ignore")
for s in ascii_regex.findall(self.data)
]
# Extract Unicode strings
unicode_regex = re.compile(
rb"(?:[\x20-\x7e]\x00){%d,}" % min_length
)
unicode_strings = [
s.decode("utf-16-le", errors="ignore")
for s in unicode_regex.findall(self.data)
]
all_strings = ascii_strings + unicode_strings
network_iocs = {"ipv4": set(), "domain": set(), "url": set(), "email": set()}
host_iocs = {"registry": set(), "filepath": set(), "mutex": set()}
other = {"useragent": set(), "pdb_path": set(), "bitcoin_wallet": set()}
for string in all_strings:
for category, pattern in patterns.items():
for match in pattern.findall(string):
if category in network_iocs:
network_iocs[category].add(match)
elif category in host_iocs:
host_iocs[category].add(match)
else:
other[category].add(match)
# Filter private IPs
private_prefixes = ("10.", "172.16.", "172.17.", "172.18.", "172.19.",
"172.20.", "172.21.", "172.22.", "172.23.", "172.24.",
"172.25.", "172.26.", "172.27.", "172.28.", "172.29.",
"172.30.", "172.31.", "192.168.", "127.", "0.", "255.")
network_iocs["ipv4"] = {
ip for ip in network_iocs["ipv4"]
if not ip.startswith(private_prefixes)
}
# Filter common benign domains
benign_domains = {
"microsoft.com", "windows.com", "google.com", "w3.org",
"xmlsoap.org", "openxmlformats.org", "schemas.microsoft.com",
}
network_iocs["domain"] = {
d for d in network_iocs["domain"]
if not any(d.endswith(b) for b in benign_domains)
}
self.iocs["network_iocs"] = {k: sorted(v) for k, v in network_iocs.items() if v}
self.iocs["host_iocs"] = {k: sorted(v) for k, v in host_iocs.items() if v}
self.iocs["suspicious_strings"] = {k: sorted(v) for k, v in other.items() if v}
def scan_yara(self, rules_path: str):
"""Scan with YARA rules."""
if yara is None:
print("[-] yara-python not installed, skipping YARA scan")
return
try:
if os.path.isdir(rules_path):
rule_files = {}
for f in os.listdir(rules_path):
if f.endswith((".yar", ".yara")):
rule_files[f] = os.path.join(rules_path, f)
rules = yara.compile(filepaths=rule_files)
else:
rules = yara.compile(filepath=rules_path)
matches = rules.match(data=self.data)
for match in matches:
self.iocs["yara_matches"].append({
"rule": match.rule,
"tags": match.tags,
"meta": match.meta,
"string_count": len(match.strings),
})
print(f"[+] YARA match: {match.rule} (tags: {match.tags})")
except yara.Error as e:
print(f"[-] YARA error: {e}")
def check_virustotal(self, api_key: str) -> Optional[dict]:
"""Check file hash against VirusTotal."""
import requests
sha256 = self.hashes["sha256"]
resp = requests.get(
f"https://www.virustotal.com/api/v3/files/{sha256}",
headers={"x-apikey": api_key},
timeout=30,
)
if resp.status_code == 200:
data = resp.json().get("data", {}).get("attributes", {})
stats = data.get("last_analysis_stats", {})
vt_result = {
"malicious": stats.get("malicious", 0),
"suspicious": stats.get("suspicious", 0),
"undetected": stats.get("undetected", 0),
"total": sum(stats.values()),
"popular_threat_name": data.get(
"popular_threat_classification", {}
).get("suggested_threat_label", ""),
"tags": data.get("tags", []),
"type_description": data.get("type_description", ""),
"names": data.get("names", [])[:5],
}
self.iocs["virustotal"] = vt_result
print(
f"[+] VT: {vt_result['malicious']}/{vt_result['total']} "
f"detections - {vt_result['popular_threat_name']}"
)
return vt_result
elif resp.status_code == 404:
print(f"[!] Hash not found on VirusTotal: {sha256}")
else:
print(f"[-] VT API error: {resp.status_code}")
return None
def generate_stix_bundle(self) -> dict:
"""Generate STIX 2.1 bundle from extracted IOCs."""
from stix2 import Bundle, Indicator, Malware, Relationship
objects = []
malware_obj = Malware(
name=self.filename,
is_family=False,
malware_types=["unknown"],
description=(
f"SHA256: {self.hashes['sha256']}\n"
f"MD5: {self.hashes['md5']}"
),
allow_custom=True,
)
objects.append(malware_obj)
# Hash indicator
hash_ind = Indicator(
name=f"File hash: {self.hashes['sha256'][:16]}...",
pattern=f"[file:hashes.'SHA-256' = '{self.hashes['sha256']}']",
pattern_type="stix",
valid_from=datetime.utcnow().strftime("%Y-%m-%dT%H:%M:%SZ"),
indicator_types=["malicious-activity"],
allow_custom=True,
)
objects.append(hash_ind)
objects.append(Relationship(
relationship_type="indicates",
source_ref=hash_ind.id,
target_ref=malware_obj.id,
))
# Network indicators
for ip in self.iocs.get("network_iocs", {}).get("ipv4", []):
ind = Indicator(
name=f"C2 IP: {ip}",
pattern=f"[ipv4-addr:value = '{ip}']",
pattern_type="stix",
valid_from=datetime.utcnow().strftime("%Y-%m-%dT%H:%M:%SZ"),
indicator_types=["malicious-activity"],
allow_custom=True,
)
objects.append(ind)
objects.append(Relationship(
relationship_type="indicates",
source_ref=ind.id,
target_ref=malware_obj.id,
))
for domain in self.iocs.get("network_iocs", {}).get("domain", []):
ind = Indicator(
name=f"C2 Domain: {domain}",
pattern=f"[domain-name:value = '{domain}']",
pattern_type="stix",
valid_from=datetime.utcnow().strftime("%Y-%m-%dT%H:%M:%SZ"),
indicator_types=["malicious-activity"],
allow_custom=True,
)
objects.append(ind)
objects.append(Relationship(
relationship_type="indicates",
source_ref=ind.id,
target_ref=malware_obj.id,
))
bundle = Bundle(objects=objects, allow_custom=True)
return json.loads(bundle.serialize())
def get_report(self) -> dict:
"""Get complete IOC extraction report."""
return self.iocs
def main():
parser = argparse.ArgumentParser(description="Malware IOC Extraction Tool")
parser.add_argument("--file", required=True, help="Path to malware sample")
parser.add_argument("--output", default="iocs.json", help="Output IOC file")
parser.add_argument("--yara-rules", help="YARA rules file or directory")
parser.add_argument("--vt-check", action="store_true", help="Check VirusTotal")
parser.add_argument("--vt-key", help="VirusTotal API key")
parser.add_argument("--stix-output", help="Output STIX 2.1 bundle file")
parser.add_argument(
"--min-string-length", type=int, default=4,
help="Minimum string length for extraction",
)
args = parser.parse_args()
if not os.path.isfile(args.file):
print(f"[-] File not found: {args.file}")
sys.exit(1)
print(f"[*] Analyzing: {args.file}")
extractor = MalwareIOCExtractor(args.file)
print("[*] Calculating hashes...")
print(f" MD5: {extractor.hashes['md5']}")
print(f" SHA1: {extractor.hashes['sha1']}")
print(f" SHA256: {extractor.hashes['sha256']}")
print("[*] Parsing PE structure...")
extractor.analyze_pe()
print("[*] Extracting strings and IOC patterns...")
extractor.extract_strings(min_length=args.min_string_length)
if args.yara_rules:
print(f"[*] Scanning with YARA rules: {args.yara_rules}")
extractor.scan_yara(args.yara_rules)
if args.vt_check and args.vt_key:
print("[*] Checking VirusTotal...")
extractor.check_virustotal(args.vt_key)
report = extractor.get_report()
with open(args.output, "w") as f:
json.dump(report, f, indent=2, default=str)
print(f"[+] IOC report saved to {args.output}")
if args.stix_output:
print("[*] Generating STIX 2.1 bundle...")
bundle = extractor.generate_stix_bundle()
with open(args.stix_output, "w") as f:
json.dump(bundle, f, indent=2)
print(f"[+] STIX bundle saved to {args.stix_output}")
# Print summary
net = report.get("network_iocs", {})
host = report.get("host_iocs", {})
print(f"\n=== IOC Summary ===")
print(f" IPs: {len(net.get('ipv4', []))}")
print(f" Domains: {len(net.get('domain', []))}")
print(f" URLs: {len(net.get('url', []))}")
print(f" Registry keys: {len(host.get('registry', []))}")
print(f" File paths: {len(host.get('filepath', []))}")
print(f" YARA matches: {len(report.get('yara_matches', []))}")
if __name__ == "__main__":
main()