resolve-pr-feedback

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

• Third-party content exposure detected (high risk: 0.95). Yes—at runtime the required workflow calls scripts/get-pr-comments which uses gh api graphql to ingest outsiders’ GitHub PR review-thread bodies, comment bodies, and review bodies (free text) and passes them into the agent’s context for subsequent triage/fix.