rest-graphql-debug

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and parse external vendor/docs and arbitrary URLs (e.g., web_extract(urls=["https://docs.example.com/api/v1/users"]) and terminal/curl calls to https://api.example.com), so it will ingest public third‑party content that can materially influence subsequent tool actions.