skill-quality-reviewer

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious code, obfuscation, or data exfiltration attempts were detected. All behaviors align with the skill's documented auditing purpose.
  • [COMMAND_EXECUTION]: The skill performs local directory listings and executes its own utility scripts.
  • Evidence: Uses 'ls -la' to check for skill file existence.
  • Evidence: Invokes 'scripts/extract-yaml.sh' and 'scripts/skill-audit.py' for data extraction and analysis.
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection through the files it evaluates.
  • Ingestion points: Content of external 'SKILL.md' files.
  • Boundary markers: No specific delimiters or safety instructions found in script logic.
  • Capability inventory: Directory listing, shell/python script execution, and writing report files to disk.
  • Sanitization: Uses standard regular expressions for parsing specific fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 04:40 PM