api-review

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses gh pr view <number> --comments / gh issue view <number> --comments and reads PR/issue bodies and diffs, which are outsider-authored free text (e.g., comments and descriptions by non-operating users) that can be ingested into the agent’s LLM context.