ClawHub
Back to skill

Security audit

Vulnerability Prioritizer

Security checks for vulnerabilities and agentic risk

Overview

This skill gives vulnerability-prioritization guidance and uses public vulnerability data sources in a way that matches its stated purpose.

Before installing, confirm you are comfortable with the agent querying public vulnerability APIs with CVE IDs from your scan results and inspecting local dependency/import data for reachability. No hidden persistence or unrelated high-impact behavior was found.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

YARA rule 'c2_framework_indicators': Command-and-control framework indicators (Cobalt Strike, Metasploit, Sliver, etc.) [malware]

Critical
Category
YARA Match
Confidence
85% confidence
Finding

YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).

Content

Scanner excerpt · SKILL.md (reported line 95)May include surrounding context.

, common services → 1.5× multiplier

Step 5: Calculate Composite Risk Score

text
Risk Score = CVSS_normalized × EPSS_weight × asset_multiplier × exploit_maturity

Where:
- CVSS_normalized = CVSS / 10 (0-1 range)
- EPSS_weight = 1 + (EPSS × 10)  (EPSS 0.5 → 6× weight)
- asset_multiplier = product of applicable multipliers
- exploit_maturity:
  - In CISA KEV = 5.0
  - Public exploit (Metasploit, ExploitDB) = 3.0
  - PoC available = 2.0
  - Theoretical = 1.0

Step 6: Generate Prioritized Report

markdown
# Vulnerability Prioritization Report

## Summary
- Total vulnerabilities: 142
- After prioritization: 12 critical, 23 high, 45 medium, 62 low
- Remediation effort: ~3 days for critical+high

## 🚨 Critical Priority (patch within 24h)
| Rank | CVE | CVSS | EPSS | KEV | Package | Risk Score | Fix |
|------|-----|------|------|-----|---------|-----------|-----|
| 1 | CVE-2024-1234 | 9.8 | 0.87 | ✅ | openssl 3.0.1 | 48.2 | Upgrade to 3.0.15 |
| 2 | CVE-2024-567

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 46)May include surrounding context.

bash
# Fetch EPSS scores (Exploit Prediction Scoring System)
# EPSS API: probability of exploitation in next 30 days
curl -s "https://api.first.org/data/v1/epss?cve=CVE-2024-1234,CVE-2024-5678" | \
  python3 -c "
import json, sys
data = json.load(sys.stdin)

Static analysis

No suspicious patterns detected.