review-prompt-composer

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes multiple Git commands (e.g., git rev-parse, git diff, git ls-files) via subprocesses in scripts/write_review_prompt.py to resolve repository state and calculate scope digests. These are used for their intended purpose of inventorying local changes and ensuring the 'freshness' of the review prompt.
  • [SAFE]: The skill implements a 'Gate sensitive prompt content' step (Category 3 in SKILL.md) and corresponding logic in the Python script to detect and block the inclusion of private keys or credential-bearing URLs in the generated artifacts. It operates strictly on the local working tree and does not perform network operations or exfiltrate data. The use of subprocess.run is restricted to local Git commands and is non-malicious.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 02:25 AM
Security Audit — agent-trust-hub — review-prompt-composer