httpx

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md documentation includes numerous runtime examples (e.g., Basic Usage, Async Requests, fetch_all, and Integration Examples like FastAPI/Django) that call client.get/post on public URLs (e.g., "https://example.com", "https://api.example.com", Stack Overflow/Discord links) and parse response.text/response.json, which clearly shows the agent fetching and interpreting untrusted third‑party web content as part of its workflow.