resolve-pr-feedback

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and ingests user-generated GitHub PR review threads and comments (see SKILL.md "Fetch Feedback" and REFERENCE.md GraphQL queries for reviewThreads/comments), and those untrusted texts are read and used to triage, fix code, and decide actions—creating a clear avenue for indirect prompt injection.