babysit-pr

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Process Review Comments" step explicitly uses gh api graphql to fetch pull request reviewThreads (including comment bodies) and gh run view to fetch CI logs, and the workflow requires the agent to read, classify, and act on those user-generated review comments and logs (potentially changing code and replies), so untrusted third-party content can materially influence actions.