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 viewandgit fetchas described inSKILL.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
ghtool inSKILL.md. - Sanitization: The workflow incorporates a safety mechanism that compares the
ORIGINAL_TREEhash against the new state usinggit rev-parseto ensure no unintended behavior changes were introduced by the cleanup process.
Audit Metadata