make-pr-easy-to-review
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from pull request titles, descriptions, and commit history. Ingestion points: The agent fetches pull request details using
gh pr view(SKILL.md). Boundary markers: No explicit boundaries or instructions to ignore embedded content are defined. Capability inventory: The skill usesgitfor inspection and history modification, andghfor viewing PRs (SKILL.md). Sanitization: No sanitization of ingested content is performed. - [SAFE]: Despite the data ingestion surface, the skill is considered safe as it includes explicit guardrails. It verifies that the code tree hash remains identical after cleanup using
git rev-parseand requires explicit user approval before performing destructive actions like force-pushing.
Audit Metadata