ready-pr

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

• Third-party content exposure detected (medium risk: 0.30). In workflows/ready-for-merge.md, the agent ingests outsider-authored free text from GitHub by fetching and triaging the PR’s top-level comments, review bodies, and inline review threads via GraphQL/REST (steps 9–11, 14–15, 17), and then uses that text to decide what to reply or resolve.