preen-review-instructions

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes internal documentation files (such as REVIEW.md and CLAUDE.md) to audit their content. These files could potentially contain indirect prompt instructions designed to influence the agent's behavior during the auditing or updating process.
  • Ingestion points: Reads from various repository documentation files including REVIEW.md, .gemini/INSTRUCTIONS.md, and compliance docs.
  • Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded commands within the files it audits.
  • Capability inventory: Includes file system reads via rg (ripgrep), ls, and cat, as well as git repository metadata access.
  • Sanitization: The skill identifies gaps in documentation but lacks explicit sanitization when interpolating file content into prompts for scripts like solicitClaudeCodeReview.sh.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:12 PM