clean-code
Fail
Audited by Gen Agent Trust Hub on Feb 13, 2026
Risk Level: HIGHCOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION] (HIGH): The 'Verification Scripts' section mandates that agents execute Python scripts located in hidden directories (e.g., '.agent/skills/vulnerability-scanner/scripts/security_scan.py .'). This allows for execution of unverified local files not contained within this skill bundle.
- [PROMPT_INJECTION] (MEDIUM): The skill uses metadata and markdown headers like 'priority: CRITICAL' and 'MANDATORY' to override default agent constraints and prioritization.
- [INDIRECT_PROMPT_INJECTION] (HIGH): The skill creates a high-risk surface area by ingesting untrusted data (user bug reports), modifying code files without sanitization or boundary markers, and then executing scripts on the modified codebase. Evidence: Ingestion point in SKILL.md (AI Coding Style); no boundary markers or sanitization; capabilities include file-write and subprocess calls via python.
Recommendations
- AI detected serious security threats
Audit Metadata