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-triage-with-yara/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.

381
vendor-new/Anthropic-Cybersecurity-Skills/skills/performing-malware-triage-with-yara/SKILL.md Normal file
View File

@@ -0,0 +1,381 @@
---
name: performing-malware-triage-with-yara
description: 'Performs rapid malware triage and classification using YARA rules that
match file patterns, strings, byte sequences, and structural characteristics against
known malware families and suspicious indicators, covering rule writing, scanning,
and integration into analysis pipelines. Use when classifying a batch of malware
samples against known family signatures, writing detection rules for a newly
analyzed malware family, or performing signature-based malware triage.
'
domain: cybersecurity
subdomain: malware-analysis
tags:
- malware
- YARA
- triage
- classification
- pattern-matching
version: 1.0.0
author: mahipal
license: Apache-2.0
nist_csf:
- DE.AE-02
- RS.AN-03
- ID.RA-01
- DE.CM-01
mitre_attack:
- T1027
- T1055
- T1140
- T1497
- T0816
---
# Performing Malware Triage with YARA
## When to Use
- Rapidly classifying a large batch of malware samples against known family signatures
- Writing detection rules for a newly analyzed malware family based on unique byte patterns
- Scanning file shares, endpoints, or memory dumps for indicators of a specific threat
- Building automated triage pipelines that classify samples before manual analysis
- Hunting for variants of a known threat across an enterprise using YARA scans
**Do not use** as the sole analysis method; YARA triage identifies known patterns but does not reveal new or unknown malware behaviors.
## Prerequisites
- YARA 4.x installed (`apt install yara` or `pip install yara-python`)
- YARA rule repositories (YARA-Rules, awesome-yara, Malpedia rules, Florian Roth's signature-base)
- Python 3.8+ with `yara-python` for scripted scanning
- Sample collection organized in a directory structure for batch scanning
- Understanding of PE file format, hex patterns, and regular expressions for rule writing
## Workflow
### Step 1: Scan Samples with Existing Rule Sets
Apply community and commercial YARA rules to classify samples:
```bash
# Scan a single file
yara -s malware_rules.yar suspect.exe
# Scan a directory of samples
yara -r malware_rules.yar /path/to/samples/
# Scan with multiple rule files
yara -r rules/apt_rules.yar rules/ransomware_rules.yar rules/trojan_rules.yar suspect.exe
# Scan with timeout (prevent hanging on large files)
yara -t 30 malware_rules.yar suspect.exe
# Scan and show matching strings
yara -s -r malware_rules.yar suspect.exe
# Scan with compiled rules (faster for repeated scans)
yarac malware_rules.yar compiled_rules.yarc
yara compiled_rules.yarc suspect.exe
```
```bash
# Download community rule sets
git clone https://github.com/Yara-Rules/rules.git yara-community-rules
git clone https://github.com/Neo23x0/signature-base.git signature-base
# Scan with signature-base
yara -r signature-base/yara/*.yar suspect.exe
```
### Step 2: Write Rules for Unique String Patterns
Create YARA rules based on strings extracted during malware analysis:
```
rule MalwareX_Strings {
meta:
description = "Detects MalwareX based on unique strings"
author = "analyst"
date = "2025-09-15"
reference = "Internal Analysis Report #1547"
hash = "e3b0c44298fc1c149afbf4c8996fb924"
tlp = "WHITE"
strings:
// C2 URL pattern
$url1 = "/gate.php?id=" ascii
$url2 = "/panel/connect.php" ascii
// Unique mutex name
$mutex = "Global\\CryptLocker_2025" ascii wide
// User-Agent string
$ua = "Mozilla/5.0 (compatible; MSIE 10.0)" ascii
// Registry persistence path
$reg = "Software\\Microsoft\\Windows\\CurrentVersion\\Run\\WindowsUpdate" ascii
// Campaign identifier
$campaign = "campaign_2025_q3" ascii
condition:
uint16(0) == 0x5A4D and // PE file (MZ header)
filesize < 500KB and // Size constraint
($url1 or $url2) and // At least one C2 URL
($mutex or $campaign) and // Campaign identifier
$ua // Specific User-Agent
}
```
### Step 3: Write Rules for Byte Patterns
Create rules matching specific code sequences:
```
rule MalwareX_Decryptor {
meta:
description = "Detects MalwareX XOR decryption routine"
author = "analyst"
date = "2025-09-15"
strings:
// XOR decryption loop (x86 assembly)
// mov al, [esi+ecx]
// xor al, [edi+ecx]
// mov [esi+ecx], al
// inc ecx
// cmp ecx, edx
// jl loop
$xor_loop = { 8A 04 0E 32 04 0F 88 04 0E 41 3B CA 7C F3 }
// RC4 KSA initialization (256-byte loop)
$rc4_ksa = { 33 C0 88 04 ?8 40 3D 00 01 00 00 7? }
// Embedded RSA public key marker
$rsa_key = { 06 02 00 00 00 A4 00 00 52 53 41 31 } // PUBLICKEYBLOB
condition:
uint16(0) == 0x5A4D and
($xor_loop or $rc4_ksa) and
$rsa_key
}
```
### Step 4: Write Rules with PE Module
Leverage YARA's PE module for structural detection:
```
import "pe"
import "hash"
import "math"
rule MalwareX_PE_Characteristics {
meta:
description = "Detects MalwareX by PE structure and imports"
author = "analyst"
condition:
pe.is_pe and
// Compiled within specific timeframe
pe.timestamp > 1693526400 and // After 2023-09-01
pe.timestamp < 1727740800 and // Before 2024-10-01
// Specific import hash
pe.imphash() == "a1b2c3d4e5f6a7b8c9d0e1f2a3b4c5d6" or
// Suspicious import combination
(
pe.imports("kernel32.dll", "VirtualAllocEx") and
pe.imports("kernel32.dll", "WriteProcessMemory") and
pe.imports("kernel32.dll", "CreateRemoteThread") and
pe.imports("wininet.dll", "InternetOpenA")
) or
// High entropy .text section (packed)
(
for any section in pe.sections : (
section.name == ".text" and
math.entropy(section.raw_data_offset, section.raw_data_size) > 7.0
)
)
}
rule MalwareX_Rich_Header {
meta:
description = "Detects MalwareX by Rich header hash"
condition:
pe.is_pe and
hash.md5(pe.rich_signature.clear_data) == "abc123def456abc123def456abc123de"
}
```
### Step 5: Batch Triage with Python
Automate scanning of sample collections:
```python
import yara
import os
import json
import hashlib
from datetime import datetime
# Compile all rule files
rule_files = {
"apt": "rules/apt_rules.yar",
"ransomware": "rules/ransomware_rules.yar",
"trojan": "rules/trojan_rules.yar",
"custom": "rules/custom_rules.yar",
}
rules = yara.compile(filepaths=rule_files)
# Scan sample directory
results = []
sample_dir = "/path/to/samples"
for filename in os.listdir(sample_dir):
filepath = os.path.join(sample_dir, filename)
if not os.path.isfile(filepath):
continue
with open(filepath, "rb") as f:
data = f.read()
sha256 = hashlib.sha256(data).hexdigest()
matches = rules.match(filepath)
result = {
"filename": filename,
"sha256": sha256,
"size": len(data),
"matches": [],
"classification": "UNKNOWN",
}
for match in matches:
result["matches"].append({
"rule": match.rule,
"namespace": match.namespace,
"tags": match.tags,
"strings": [(hex(s[0]), s[1], s[2].decode("utf-8", errors="replace")[:100])
for s in match.strings] if match.strings else []
})
if result["matches"]:
result["classification"] = result["matches"][0]["namespace"].upper()
results.append(result)
# Summary
classified = sum(1 for r in results if r["classification"] != "UNKNOWN")
print(f"Scanned: {len(results)} samples")
print(f"Classified: {classified} ({classified/len(results)*100:.1f}%)")
print(f"Unknown: {len(results)-classified}")
# Export results
with open("triage_results.json", "w") as f:
json.dump(results, f, indent=2)
```
### Step 6: Validate and Optimize Rules
Test rules for false positives and performance:
```bash
# Test rule syntax
yara -C custom_rules.yar
# Scan known-clean directory to check false positives
yara -r custom_rules.yar /path/to/clean_files/ > false_positives.txt
wc -l false_positives.txt
# Benchmark rule performance
time yara -r custom_rules.yar /path/to/large_sample_collection/
# Profile individual rule performance
yara -p custom_rules.yar suspect.exe
```
## Key Concepts
| Term | Definition |
|------|------------|
| **YARA Rule** | Pattern matching rule defining strings, byte sequences, and conditions that identify a specific file or malware family |
| **Condition** | Boolean expression combining string matches, file properties, and module functions to determine if a rule matches |
| **Hex String** | Byte pattern with optional wildcards (??) and jumps ([N-M]) for matching machine code or binary data |
| **PE Module** | YARA module providing access to PE file properties (imports, sections, timestamps, resources) for structural matching |
| **Imphash** | MD5 hash of a PE file's import table; samples from the same family often share import hashes |
| **Rich Header** | Undocumented PE structure containing compiler/linker metadata; consistent within malware build environments |
| **YARA-C** | Compiled YARA rule format enabling faster scanning by pre-compiling rules for repeated use |
## Tools & Systems
- **YARA**: Pattern matching engine for identifying and classifying malware based on text, hex, and structural patterns
- **yara-python**: Python bindings for YARA enabling scripted scanning, rule compilation, and integration with analysis pipelines
- **yarGen**: Automatic YARA rule generator that creates rules from malware samples by identifying unique strings and opcodes
- **YARA-Rules (GitHub)**: Community-maintained repository of YARA rules covering malware families, exploits, and suspicious indicators
- **Malpedia YARA**: Curated YARA rules from the Malpedia malware encyclopedia with high-quality family-specific rules
## Common Scenarios
### Scenario: Creating Detection Rules for a New Malware Family
**Context**: Reverse engineering of a new malware sample has identified unique strings, byte patterns, and PE characteristics. YARA rules are needed for enterprise-wide hunting and ongoing detection.
**Approach**:
1. Extract unique strings from the unpacked binary (C2 URLs, mutex names, registry paths)
2. Identify unique byte sequences from the encryption routine or C2 protocol (from Ghidra analysis)
3. Record PE characteristics (imphash, Rich header hash, section names, compilation timestamp range)
4. Write a YARA rule combining string, byte pattern, and PE module conditions
5. Test against the known malware samples to confirm true positive detection
6. Test against a clean file corpus (Windows system files, common applications) to verify zero false positives
7. Deploy to enterprise scanning infrastructure and threat intelligence platform
**Pitfalls**:
- Writing rules too specific to a single sample (will not detect variants with minor changes)
- Writing rules too generic (matching legitimate software, causing false positives)
- Using strings that appear in common libraries or frameworks (e.g., OpenSSL strings)
- Not testing on a sufficiently large clean corpus before deployment
## Output Format
```
YARA TRIAGE RESULTS
=====================
Scan Date: 2025-09-15
Rule Sets: apt_rules (847 rules), ransomware_rules (312 rules),
trojan_rules (1,204 rules), custom_rules (45 rules)
Samples Scanned: 2,500
Processing Time: 47 seconds
CLASSIFICATION SUMMARY
APT: 12 samples (0.5%)
Ransomware: 187 samples (7.5%)
Trojan: 423 samples (16.9%)
Unknown: 1,878 samples (75.1%)
TOP MATCHING RULES
Rule Matches Family
MalwareX_C2_Beacon 45 MalwareX
LockBit3_Ransom_Note 38 LockBit 3.0
Emotet_Epoch5_Loader 32 Emotet
CobaltStrike_Beacon_Config 28 Cobalt Strike
QakBot_DLL_Loader 25 QakBot
SAMPLE DETAIL
File: suspect.exe
SHA-256: e3b0c44298fc1c149afbf4c8996fb924...
Matches:
[1] MalwareX_Strings (custom)
- $url1 at 0x4A20: "/gate.php?id="
- $mutex at 0x5100: "Global\\CryptLocker_2025"
[2] MalwareX_Decryptor (custom)
- $xor_loop at 0x401200: { 8A 04 0E 32 04 0F ... }
[3] MalwareX_PE_Characteristics (custom)
- PE import combination matched
Classification: MALWAREX (HIGH CONFIDENCE)
```

54
vendor-new/Anthropic-Cybersecurity-Skills/skills/performing-malware-triage-with-yara/references/api-reference.md Normal file
View File

@@ -0,0 +1,54 @@
# API Reference: Malware Triage with YARA
## yara-python API
```python
import yara
# Compile from files
rules = yara.compile(filepaths={"ns1": "rules.yar"})
# Compile from string
rules = yara.compile(source='rule test { condition: true }')
# Scan file
matches = rules.match("/path/to/sample")
# Scan data
matches = rules.match(data=open("sample", "rb").read())
```
## Match Object Attributes
| Attribute | Type | Description |
|-----------|------|-------------|
| `match.rule` | str | Name of the matching rule |
| `match.namespace` | str | Rule file namespace |
| `match.tags` | list | Tags from the rule definition |
| `match.meta` | dict | Meta fields (author, description, hash) |
| `match.strings` | list | Matched strings: (offset, identifier, data) |
## YARA CLI
| Command | Description |
|---------|-------------|
| `yara rules.yar sample.exe` | Scan file against rules |
| `yara -r rules.yar /dir/` | Recursive directory scan |
| `yara -s rules.yar sample.exe` | Show matching strings |
| `yarac rules.yar compiled.yarc` | Compile rules for faster loading |
| `yara -C rules.yar` | Check rule syntax |
## Python Libraries
| Library | Version | Purpose |
|---------|---------|---------|
| `yara-python` | >=4.3 | YARA rule compilation and scanning |
| `hashlib` | stdlib | Sample hashing (SHA-256, MD5) |
## References
- YARA documentation: https://yara.readthedocs.io/
- yara-python: https://github.com/VirusTotal/yara-python
- YARA-Rules community: https://github.com/Yara-Rules/rules
- Signature-base: https://github.com/Neo23x0/signature-base
- yarGen rule generator: https://github.com/Neo23x0/yarGen

182
vendor-new/Anthropic-Cybersecurity-Skills/skills/performing-malware-triage-with-yara/scripts/agent.py Normal file
View File

@@ -0,0 +1,182 @@
#!/usr/bin/env python3
"""Agent for performing malware triage with YARA.
Compiles and applies YARA rules to classify malware samples,
perform batch scanning, and generate triage reports.
"""
import yara
import sys
import json
import hashlib
from pathlib import Path
from collections import defaultdict
from datetime import datetime
class YaraTriageAgent:
"""Batch malware triage and classification using YARA rules."""
def __init__(self, output_dir):
self.output_dir = Path(output_dir)
self.output_dir.mkdir(parents=True, exist_ok=True)
self.rules = None
self.results = []
def compile_rules(self, rule_paths):
"""Compile YARA rules from file paths or directories."""
filepaths = {}
for path in rule_paths:
p = Path(path)
if p.is_file() and p.suffix in (".yar", ".yara"):
filepaths[p.stem] = str(p)
elif p.is_dir():
for rule_file in p.rglob("*.yar"):
filepaths[rule_file.stem] = str(rule_file)
for rule_file in p.rglob("*.yara"):
filepaths[rule_file.stem] = str(rule_file)
if not filepaths:
raise ValueError(f"No YARA rule files found in: {rule_paths}")
self.rules = yara.compile(filepaths=filepaths)
return len(filepaths)
def scan_file(self, filepath):
"""Scan a single file against compiled YARA rules."""
filepath = Path(filepath)
if not filepath.is_file():
return None
with open(filepath, "rb") as f:
data = f.read()
sha256 = hashlib.sha256(data).hexdigest()
md5 = hashlib.md5(data).hexdigest()
matches = self.rules.match(data=data)
result = {
"filename": filepath.name,
"path": str(filepath),
"sha256": sha256,
"md5": md5,
"size": len(data),
"matches": [],
"match_count": len(matches),
"classification": "UNKNOWN",
}
for match in matches:
match_info = {
"rule": match.rule,
"namespace": match.namespace,
"tags": match.tags,
"meta": match.meta,
"strings": [],
}
if match.strings:
for string_match in match.strings[:10]:
match_info["strings"].append({
"identifier": string_match[1],
"offset": hex(string_match[0]),
"data": string_match[2].decode("utf-8", errors="replace")[:80],
})
result["matches"].append(match_info)
if result["matches"]:
result["classification"] = result["matches"][0].get("namespace", "DETECTED").upper()
return result
def scan_directory(self, sample_dir, recursive=True):
"""Scan all files in a directory."""
sample_path = Path(sample_dir)
glob_fn = sample_path.rglob if recursive else sample_path.glob
for filepath in glob_fn("*"):
if filepath.is_file() and filepath.stat().st_size > 0:
result = self.scan_file(filepath)
if result:
self.results.append(result)
return self.results
def get_classification_summary(self):
"""Summarize scan results by classification."""
summary = defaultdict(int)
for result in self.results:
summary[result["classification"]] += 1
return dict(sorted(summary.items(), key=lambda x: x[1], reverse=True))
def get_top_rules(self, limit=20):
"""Get most frequently matching rules."""
rule_counts = defaultdict(int)
for result in self.results:
for match in result["matches"]:
rule_counts[match["rule"]] += 1
return dict(sorted(rule_counts.items(), key=lambda x: x[1], reverse=True)[:limit])
def generate_report(self):
"""Generate comprehensive triage report."""
classified = [r for r in self.results if r["classification"] != "UNKNOWN"]
unknown = [r for r in self.results if r["classification"] == "UNKNOWN"]
report = {
"scan_date": datetime.utcnow().isoformat(),
"total_scanned": len(self.results),
"classified": len(classified),
"unknown": len(unknown),
"classification_rate": round(
len(classified) / max(len(self.results), 1) * 100, 1
),
"classification_summary": self.get_classification_summary(),
"top_matching_rules": self.get_top_rules(),
"detected_samples": [
{
"filename": r["filename"],
"sha256": r["sha256"],
"classification": r["classification"],
"rules_matched": [m["rule"] for m in r["matches"]],
}
for r in classified
],
}
report_path = self.output_dir / "yara_triage_report.json"
with open(report_path, "w") as f:
json.dump(report, f, indent=2)
print(f"YARA Triage Results")
print(f"={'=' * 40}")
print(f"Scanned: {report['total_scanned']}")
print(f"Classified: {report['classified']} ({report['classification_rate']}%)")
print(f"Unknown: {report['unknown']}")
print(f"\nClassification Summary:")
for cls, count in report["classification_summary"].items():
print(f" {cls}: {count}")
print(f"\nTop Rules:")
for rule, count in list(report["top_matching_rules"].items())[:10]:
print(f" {rule}: {count} matches")
return report
def main():
if len(sys.argv) < 3:
print("Usage: agent.py <rules_path> <samples_dir> [output_dir]")
print(" rules_path: YARA rule file or directory of .yar files")
print(" samples_dir: Directory of files to scan")
sys.exit(1)
rules_path = sys.argv[1]
samples_dir = sys.argv[2]
output_dir = sys.argv[3] if len(sys.argv) > 3 else "./triage_output"
agent = YaraTriageAgent(output_dir)
rule_count = agent.compile_rules([rules_path])
print(f"Compiled {rule_count} rule files")
agent.scan_directory(samples_dir)
agent.generate_report()
if __name__ == "__main__":
main()