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-threat-hunting-with-yara-rules/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.

433
vendor-new/Anthropic-Cybersecurity-Skills/skills/performing-threat-hunting-with-yara-rules/SKILL.md Normal file
View File

@@ -0,0 +1,433 @@
---
name: performing-threat-hunting-with-yara-rules
description: 'Use YARA pattern-matching rules to hunt for malware, suspicious files,
and indicators of compromise across filesystems and memory dumps. Covers rule authoring,
yara-python scanning, and integration with threat intel feeds.
'
domain: cybersecurity
subdomain: threat-hunting
tags:
- yara
- malware-detection
- threat-hunting
- pattern-matching
version: '1.0'
author: mahipal
license: Apache-2.0
d3fend_techniques:
- Executable Denylisting
- Execution Isolation
- File Metadata Consistency Validation
- Content Format Conversion
- File Content Analysis
nist_csf:
- DE.CM-01
- DE.AE-02
- DE.AE-07
- ID.RA-05
mitre_attack:
- T1046
- T1057
- T1082
- T1083
- T1005
---
# Performing Threat Hunting with YARA Rules
Scan files, directories, and memory dumps using YARA rules to identify
malware families, suspicious patterns, and IOC matches.
## When to Use
- Proactively hunting for unknown malware variants across network shares, endpoints, and email attachments
- Scanning quarantine directories or sandbox outputs for malware family classification
- Searching process memory dumps for injected code or in-memory-only payloads
- Validating threat intelligence IOCs against a large corpus of collected samples
- Triaging incident response artifacts to identify known malware families quickly
- Building automated detection pipelines that scan new files on ingestion
**Do not use** for real-time endpoint protection (use EDR agents instead); YARA scanning is best suited for batch hunting, triage, and post-collection analysis where scan latency is acceptable.
## Prerequisites
- YARA 4.x installed (`apt install yara` on Debian/Ubuntu, `brew install yara` on macOS)
- Python 3.8+ with `yara-python` (`pip install yara-python`)
- `yarGen` for automated rule generation (`git clone https://github.com/Neo23x0/yarGen`)
- Sample malware corpus or suspicious files for scanning (from malware zoos, VT, or incident artifacts)
- Optional: `pefile` for PE header analysis, `malduck` for memory carving
- Threat intel YARA rule sets (e.g., YARA-Rules community repository, Florian Roth signature-base)
## Workflow
### Step 1: Install YARA and Python Bindings
```bash
# Linux
sudo apt update && sudo apt install -y yara
# Python bindings
pip install yara-python
# Verify installation
yara --version
python3 -c "import yara; print(yara.YARA_VERSION)"
```
### Step 2: Write a Basic YARA Rule
Create rules that match on strings, hex patterns, and file metadata:
```yara
// File: rules/emotet_loader.yar
rule Emotet_Loader_2026 {
meta:
author = "Threat Intel Team"
description = "Detects Emotet first-stage loader DLL"
date = "2026-01-20"
reference = "https://attack.mitre.org/software/S0367/"
mitre_attack = "T1059.001, T1055.001"
severity = "critical"
strings:
// Emotet export function name patterns
$export1 = "DllRegisterServer" ascii
$export2 = "RunDLL" ascii nocase
// Obfuscated string decryption routine
$decrypt_loop = { 8B 45 ?? 33 45 ?? 89 45 ?? 8B 4D ?? 03 4D ?? }
// PowerShell download cradle in embedded script
$ps_cradle = /powershell[^\n]{0,50}-e(nc|ncodedcommand)/i
// Known C2 URI patterns
$uri1 = "/wp-content/uploads/" ascii
$uri2 = "/wp-admin/css/" ascii
$uri3 = "/wp-includes/" ascii
// PE characteristics
$mz = "MZ" at 0
condition:
$mz and
filesize < 2MB and
(
($export1 and $decrypt_loop) or
($ps_cradle and any of ($uri*)) or
(2 of ($uri*) and $decrypt_loop)
)
}
```
### Step 3: Write Advanced Rules with Modules
Use YARA modules for PE header inspection and math-based entropy checks:
```yara
import "pe"
import "math"
rule Suspicious_Packed_Executable {
meta:
author = "Threat Hunting Team"
description = "Detects PE files with high entropy sections indicating packing or encryption"
severity = "medium"
condition:
pe.is_pe and
pe.number_of_sections > 0 and
for any section in pe.sections : (
math.entropy(section.offset, section.size) > 7.2 and
section.size > 1024
) and
pe.imports("kernel32.dll", "VirtualAlloc") and
pe.imports("kernel32.dll", "VirtualProtect")
}
rule Suspicious_UPX_Modified {
meta:
description = "Detects UPX-packed binaries with tampered section names"
severity = "medium"
strings:
$upx_magic = { 55 50 58 21 } // UPX!
condition:
pe.is_pe and
$upx_magic and
not (
pe.sections[0].name == "UPX0" and
pe.sections[1].name == "UPX1"
)
}
```
### Step 4: Scan Files and Directories with yara-python
```python
import yara
import os
import json
from datetime import datetime
from pathlib import Path
def compile_rules(rule_paths):
"""Compile YARA rules from one or more .yar files."""
rule_files = {}
for i, path in enumerate(rule_paths):
namespace = Path(path).stem
rule_files[namespace] = path
return yara.compile(filepaths=rule_files)
def scan_directory(rules, target_dir, recursive=True):
"""Scan a directory for matches and return structured results."""
results = []
scan_count = 0
error_count = 0
for root, dirs, files in os.walk(target_dir):
for filename in files:
filepath = os.path.join(root, filename)
scan_count += 1
try:
matches = rules.match(filepath, timeout=60)
if matches:
for match in matches:
result = {
"file": filepath,
"rule": match.rule,
"namespace": match.namespace,
"tags": match.tags,
"meta": match.meta,
"strings": [],
"scan_time": datetime.utcnow().isoformat()
}
for offset, identifier, data in match.strings:
result["strings"].append({
"offset": hex(offset),
"identifier": identifier,
"data": data.hex() if isinstance(data, bytes) else data
})
results.append(result)
print(f" MATCH: {match.rule} -> {filepath}")
except yara.TimeoutError:
error_count += 1
print(f" TIMEOUT scanning {filepath}")
except yara.Error as e:
error_count += 1
if not recursive:
break
print(f"\nScan complete: {scan_count} files scanned, "
f"{len(results)} matches, {error_count} errors")
return results
# Compile and scan
rules = compile_rules([
"rules/emotet_loader.yar",
"rules/suspicious_packed.yar"
])
matches = scan_directory(rules, "/mnt/evidence/collected_samples/")
# Export results
with open("yara_scan_results.json", "w") as f:
json.dump(matches, f, indent=2)
```
### Step 5: Scan Process Memory Dumps
Hunt for in-memory indicators that only exist in running processes:
```python
import yara
def scan_memory_dump(rules, dump_path):
"""Scan a process memory dump for YARA matches."""
matches = rules.match(dump_path, timeout=120)
for match in matches:
print(f"Rule: {match.rule}")
print(f" Severity: {match.meta.get('severity', 'unknown')}")
for offset, identifier, data in match.strings:
# Show context around the match
print(f" String {identifier} at offset {hex(offset)}")
if len(data) <= 64:
print(f" Data: {data.hex()}")
return matches
# Rules targeting in-memory artifacts
memory_rules = yara.compile(source="""
rule Cobalt_Strike_Beacon_Memory {
meta:
description = "Detects Cobalt Strike beacon in process memory"
severity = "critical"
strings:
$config_start = { 2E 2F 2E 2F 2E 2C }
$sleep_mask = { 48 8B 44 24 ?? 48 89 44 24 ?? 48 8B 44 24 }
$named_pipe = "\\\\\\\\.\\\\pipe\\\\msagent_" ascii
$watermark = { 00 00 00 00 00 00 ?? ?? 00 00 }
condition:
2 of them
}
""")
scan_memory_dump(memory_rules, "/mnt/evidence/lsass_dump.dmp")
```
### Step 6: Generate Rules Automatically with yarGen
Use yarGen to create rules from malware samples by extracting unique strings:
```bash
# Clone and set up yarGen
git clone https://github.com/Neo23x0/yarGen.git
cd yarGen
pip install -r requirements.txt
# Download the string databases (run once)
python3 yarGen.py --update
# Generate rules from a directory of malware samples
python3 yarGen.py \
-m /mnt/evidence/malware_samples/ \
-o generated_rules.yar \
--excludegood \
-p "AutoGen" \
-a "Threat Hunting Team" \
--score 50
# Generate rules for a single sample with maximum detail
python3 yarGen.py \
-m /mnt/evidence/malware_samples/suspicious.exe \
-o single_sample_rule.yar \
--opcodes \
--debug
```
### Step 7: Integrate Community Rule Sets
Download and combine rules from public threat intelligence repositories:
```bash
# Clone Florian Roth's signature-base (large community rule set)
git clone https://github.com/Neo23x0/signature-base.git
# Clone YARA-Rules community repository
git clone https://github.com/Yara-Rules/rules.git yara-community-rules
# Clone ReversingLabs YARA rules
git clone https://github.com/reversinglabs/reversinglabs-yara-rules.git
```
```python
import yara
from pathlib import Path
def load_rule_directory(rule_dir, extensions=(".yar", ".yara")):
"""Load all YARA rules from a directory tree."""
rule_files = {}
for ext in extensions:
for rule_file in Path(rule_dir).rglob(f"*{ext}"):
namespace = rule_file.stem
# Avoid namespace collisions
if namespace in rule_files:
namespace = f"{rule_file.parent.name}_{namespace}"
rule_files[namespace] = str(rule_file)
print(f"Loading {len(rule_files)} rule files from {rule_dir}")
try:
compiled = yara.compile(filepaths=rule_files)
return compiled
except yara.SyntaxError as e:
print(f"Syntax error in rules: {e}")
# Fall back to loading rules one by one, skipping broken ones
valid_rules = {}
for ns, path in rule_files.items():
try:
yara.compile(filepath=path)
valid_rules[ns] = path
except yara.SyntaxError:
print(f" Skipping broken rule: {path}")
return yara.compile(filepaths=valid_rules)
# Load and scan with community rules
community_rules = load_rule_directory("signature-base/yara/")
matches = community_rules.match("/mnt/evidence/suspicious_file.exe", timeout=120)
for m in matches:
print(f"Matched: {m.rule} (namespace: {m.namespace})")
```
### Step 8: Build a Continuous Hunting Pipeline
Automate scanning of new files as they arrive using filesystem monitoring:
```python
import yara
import time
import json
import hashlib
from pathlib import Path
from watchdog.observers import Observer
from watchdog.events import FileSystemEventHandler
class YaraHuntingHandler(FileSystemEventHandler):
def __init__(self, rules, alert_file="yara_alerts.jsonl"):
self.rules = rules
self.alert_file = alert_file
self.scanned_hashes = set()
def on_created(self, event):
if event.is_directory:
return
self._scan_file(event.src_path)
def _scan_file(self, filepath):
# Deduplicate by file hash
try:
file_hash = hashlib.sha256(Path(filepath).read_bytes()).hexdigest()
except (PermissionError, FileNotFoundError):
return
if file_hash in self.scanned_hashes:
return
self.scanned_hashes.add(file_hash)
matches = self.rules.match(filepath, timeout=60)
if matches:
alert = {
"timestamp": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),
"file": filepath,
"sha256": file_hash,
"matches": [
{"rule": m.rule, "severity": m.meta.get("severity", "unknown")}
for m in matches
]
}
with open(self.alert_file, "a") as f:
f.write(json.dumps(alert) + "\n")
print(f"ALERT: {filepath} matched {len(matches)} rules")
# Set up continuous monitoring
rules = yara.compile(filepaths={"hunting": "rules/all_hunting_rules.yar"})
handler = YaraHuntingHandler(rules)
observer = Observer()
observer.schedule(handler, path="/mnt/quarantine/", recursive=True)
observer.start()
print("YARA hunting pipeline active. Monitoring /mnt/quarantine/ ...")
```
## Verification
- Compile all custom rules without syntax errors: `yara -w rules/*.yar /dev/null`
- Confirm rules match known-good malware samples from your test corpus (true positive validation)
- Verify rules do NOT match a goodware corpus of common system files (false positive testing)
- Test scanning performance: single file scan should complete within timeout threshold
- Validate yarGen output rules compile and produce meaningful matches against the input samples
- Check that community rule sets load without critical syntax errors after filtering
- Confirm the continuous hunting pipeline generates alerts in JSONL format when test files are dropped
- Cross-reference YARA matches against VirusTotal or sandbox results to validate detection accuracy

89
vendor-new/Anthropic-Cybersecurity-Skills/skills/performing-threat-hunting-with-yara-rules/references/api-reference.md Normal file
View File

@@ -0,0 +1,89 @@
# API Reference: Threat Hunting with YARA Rules
## yara-python Library
### Installation
```bash
pip install yara-python
```
### Compile and Scan
```python
import yara
# Compile from source string
rules = yara.compile(source='rule test { strings: $a = "malware" condition: $a }')
# Compile from file
rules = yara.compile(filepath='/path/to/rules.yar')
# Compile from directory (multiple files)
rules = yara.compile(filepaths={'ns1': '/rules/rule1.yar', 'ns2': '/rules/rule2.yar'})
# Scan file
matches = rules.match('/path/to/suspect.exe')
for m in matches:
print(m.rule, m.meta, m.strings, m.tags)
# Scan data (bytes)
matches = rules.match(data=open('/path/to/file', 'rb').read())
# Scan with timeout (seconds)
matches = rules.match('/path/to/file', timeout=60)
```
## YARA CLI
```bash
# Scan file with single rule
yara rule.yar suspect.exe
# Scan directory recursively
yara -r rules.yar /path/to/directory/
# Show matching strings
yara -s rule.yar suspect.exe
# Show metadata
yara -e rule.yar suspect.exe
# Compile rules to binary
yarac rules.yar compiled.yarc
yara compiled.yarc suspect.exe
# Scan with tag filter
yara -t malware rules.yar /path/
```
## YARA Rule Structure
```yara
rule Example_Rule {
meta:
author = "analyst"
description = "Detects example pattern"
severity = "high"
reference = "https://example.com"
strings:
$text = "suspicious_string" ascii nocase
$hex = { 4D 5A 90 00 }
$regex = /eval\(base64_decode/
condition:
uint16(0) == 0x5A4D and 2 of ($text, $hex, $regex)
}
```
## Match Object Fields
| Field | Description |
|-------|------------|
| rule | Rule name that matched |
| meta | Dict of meta key-value pairs |
| strings | List of (offset, identifier, data) tuples |
| tags | List of rule tags |
| namespace | Rule namespace |
## Community Rule Sources
| Source | URL |
|--------|-----|
| YARA-Rules | https://github.com/Yara-Rules/rules |
| Elastic YARA | https://github.com/elastic/protections-artifacts |
| Malpedia | https://malpedia.caad.fkie.fraunhofer.de |
| ThreatHunting Keywords | https://github.com/mthcht/ThreatHunting-Keywords-yara-rules |

173
vendor-new/Anthropic-Cybersecurity-Skills/skills/performing-threat-hunting-with-yara-rules/scripts/agent.py Normal file
View File

@@ -0,0 +1,173 @@
#!/usr/bin/env python3
"""Threat hunting agent using YARA rules.
Scans files and directories with yara-python, supports rule compilation,
multi-rule scanning, and structured JSON match output.
"""
import argparse
import json
import os
import sys
import hashlib
import datetime
try:
import yara
HAS_YARA = True
except ImportError:
HAS_YARA = False
BUILTIN_RULES = {
"suspicious_powershell": """
rule Suspicious_PowerShell {
meta:
description = "Detects obfuscated PowerShell patterns"
severity = "high"
strings:
$enc = "-EncodedCommand" ascii nocase
$bypass = "-ExecutionPolicy Bypass" ascii nocase
$hidden = "-WindowStyle Hidden" ascii nocase
$iex = "IEX" ascii nocase
$webclient = "Net.WebClient" ascii nocase
$downloadstring = "DownloadString" ascii nocase
condition:
2 of them
}""",
"mimikatz_strings": """
rule Mimikatz_Strings {
meta:
description = "Detects Mimikatz credential harvesting tool"
severity = "critical"
strings:
$s1 = "sekurlsa::logonpasswords" ascii nocase
$s2 = "sekurlsa::wdigest" ascii nocase
$s3 = "lsadump::sam" ascii nocase
$s4 = "privilege::debug" ascii nocase
$s5 = "gentilkiwi" ascii wide
condition:
2 of them
}""",
"webshell_generic": """
rule Webshell_Generic {
meta:
description = "Detects common webshell patterns"
severity = "high"
strings:
$php1 = "eval($_POST" ascii nocase
$php2 = "eval($_GET" ascii nocase
$php3 = "eval($_REQUEST" ascii nocase
$php4 = "base64_decode($_" ascii nocase
$asp1 = "eval(Request" ascii nocase
$jsp1 = "Runtime.getRuntime().exec" ascii
condition:
any of them
}""",
}
def compile_rules(rule_sources=None, rule_dir=None):
"""Compile YARA rules from strings or directory."""
if not HAS_YARA:
return None
if rule_dir and os.path.isdir(rule_dir):
filepaths = {}
for f in os.listdir(rule_dir):
if f.endswith((".yar", ".yara")):
filepaths[f] = os.path.join(rule_dir, f)
if filepaths:
return yara.compile(filepaths=filepaths)
if rule_sources:
combined = "\n".join(rule_sources.values())
return yara.compile(source=combined)
return yara.compile(source="\n".join(BUILTIN_RULES.values()))
def scan_file(rules, filepath):
"""Scan a single file with compiled YARA rules."""
try:
matches = rules.match(filepath)
return [
{
"rule": m.rule,
"meta": m.meta,
"strings": [
{"offset": s[0], "identifier": s[1], "data": s[2].decode("utf-8", errors="replace")[:64]}
for s in m.strings
],
"tags": list(m.tags),
}
for m in matches
]
except yara.Error as e:
return [{"error": str(e)}]
def scan_directory(rules, directory, max_size_mb=50):
"""Recursively scan directory with YARA rules."""
results = []
max_bytes = max_size_mb * 1024 * 1024
for root, _, files in os.walk(directory):
for fname in files:
fpath = os.path.join(root, fname)
try:
if os.path.getsize(fpath) > max_bytes:
continue
matches = scan_file(rules, fpath)
if matches and not any("error" in m for m in matches):
sha256 = hashlib.sha256(open(fpath, "rb").read()).hexdigest()
results.append({"file": fpath, "sha256": sha256, "matches": matches})
except (PermissionError, OSError):
continue
return results
def main():
parser = argparse.ArgumentParser(description="YARA-based threat hunting scanner")
parser.add_argument("target", nargs="?", help="File or directory to scan")
parser.add_argument("--rules-dir", help="Directory containing .yar/.yara rule files")
parser.add_argument("--max-size", type=int, default=50, help="Max file size in MB (default: 50)")
parser.add_argument("--output", "-o", help="Output JSON report path")
args = parser.parse_args()
print("[*] YARA Threat Hunting Agent")
print(f" yara-python available: {HAS_YARA}")
if not HAS_YARA:
print("[!] Install yara-python: pip install yara-python")
sys.exit(1)
rules = compile_rules(rule_dir=args.rules_dir)
if not rules:
print("[!] No rules compiled")
sys.exit(1)
report = {"timestamp": datetime.datetime.utcnow().isoformat() + "Z", "findings": []}
if args.target and os.path.isfile(args.target):
matches = scan_file(rules, args.target)
if matches:
report["findings"].append({"file": args.target, "matches": matches})
elif args.target and os.path.isdir(args.target):
report["findings"] = scan_directory(rules, args.target, args.max_size)
else:
print("[DEMO] Built-in rules available:")
for name, rule in BUILTIN_RULES.items():
desc = [l for l in rule.splitlines() if "description" in l]
print(f" {name}: {desc[0].strip() if desc else ''}")
print("\nUsage: python agent.py /path/to/scan --rules-dir /path/to/rules")
total = len(report["findings"])
print(f"\n[*] Total files with matches: {total}")
if args.output:
with open(args.output, "w") as f:
json.dump(report, f, indent=2)
print(f"[*] Report saved to {args.output}")
else:
print(json.dumps({"files_matched": total, "rules_loaded": len(BUILTIN_RULES)}, indent=2))
if __name__ == "__main__":
main()