make-pr-easy-to-review

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a controlled and verifiable approach to PR management. It uses established tools (git and gh CLI) and implements safety checks, such as comparing tree hashes (git rev-parse HEAD^{tree}) to ensure that code behavior remains unchanged during history cleanup.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external pull request descriptions and commit messages, which represents a potential injection surface.\n
  • Ingestion points: Reads PR descriptions, commit messages, and metadata via gh pr view and git commands in SKILL.md.\n
  • Boundary markers: None identified. The skill does not use specific delimiters or instructions to isolate external data from its own processing logic.\n
  • Capability inventory: Commands include git for history manipulation and gh for PR interactions.\n
  • Sanitization: None identified. The skill relies on the agent's logic to clean and summarize data rather than automated filtering or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 11:52 AM
Security Audit — agent-trust-hub — make-pr-easy-to-review