make-pr-easy-to-review

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external Pull Request descriptions and commit history, creating a potential surface for indirect instructions to influence the agent's behavior during PR cleanup.
  • Ingestion points: Processes PR metadata and commit history via gh pr view and git fetch as described in SKILL.md.
  • Boundary markers: The skill lacks explicit prompt delimiters or instructions to ignore embedded commands within the processed PR text.
  • Capability inventory: Includes capabilities to perform git history rewrites, tree inspections, and PR metadata updates via the gh tool in SKILL.md.
  • Sanitization: The workflow incorporates a safety mechanism that compares the ORIGINAL_TREE hash against the new state using git rev-parse to ensure no unintended behavior changes were introduced by the cleanup process.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 04:28 PM
Security Audit — agent-trust-hub — make-pr-easy-to-review