babysit

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs the agent to fetch and read GitHub pull request review threads and comment bodies via gh api/GraphQL (see the reviewThreads query and jq parsing), which are untrusted, user-generated third‑party contents that the agent is expected to interpret and act on (fix code, resolve threads, decide next steps).