https-outcalls

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md demonstrates canisters performing HTTPS outcalls to public endpoints (e.g., getIcpPriceUsd calls https://api.coingecko.com and postData calls https://httpbin.org) and parsing/acting on the returned response bodies as part of their workflow, which exposes the agent to untrusted third‑party content.