api-client

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly shows and directs runtime ingestion of external, public API endpoints and OpenAPI specs (e.g., npx openapi-typescript https://api.example.com/openapi.json and numerous fetch/httpx/axios examples), meaning the agent would read and act on arbitrary third‑party content that can change client behavior.