j5ik2o-gh-pr-review-follow-up

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

• Third-party content exposure detected (high risk: 0.85). Yes: the required workflow runs scripts/fetch_comments.py, which calls gh api graphql to retrieve PR comment/review bodies (body fields) authored by other users, then prints them as JSON that becomes readable LLM context for the agent.