api-client

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly makes authenticated requests to external REST APIs (see SKILL.md "When to Use" and the request/paginate/batch capabilities and examples calling https://api.github.com), parses those responses, and uses them to drive follow-up actions (pagination, retries, POSTs), so it clearly ingests untrusted third‑party/user-generated API content that can influence agent behavior.