circuit-breaker-pattern

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

• Third-party content exposure detected (high risk: 0.70). The skill's examples and guidance explicitly call out and demonstrate fetching from external APIs (e.g., fetch('https://api.example.com/data') in the TypeScript/Node examples and requests.get('https://api.example.com/data') in the Python example) and describe use with "External API calls" and "third‑party service integrations," meaning the agent would ingest untrusted third‑party responses as part of its workflow.