pr-review

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The skill's Phase 1 workflow explicitly accepts and ingests PR diffs via commands like gh pr diff <number>, meaning the agent will read user-generated GitHub PR content (and CLAUDE.md in the repo) from an external source which could contain adversarial/untrusted instructions that influence its review decisions.