resilience-patterns

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly integrates and protects calls to public external APIs (e.g., YouTube, arXiv, GitHub listed in the service inventory and circuit-breaker registry) and contains analysis/LLM workflows that will read and interpret responses from those APIs, so it clearly ingests untrusted, user-generated third‑party content.