api-integration-specialist

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

• Third-party content exposure detected (high risk: 0.80). This skill includes runtime code and examples that fetch and process arbitrary external APIs (e.g., scripts/test_api_health.py which issues requests to a user-supplied --base-url, plus functions like fetch_all_pages_offset and many requests.get calls), so it would ingest untrusted third-party content for the agent to read/interpret.