bknd-api-discovery

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

• Third-party content exposure detected (high risk: 0.90). The skill instructs the agent to fetch and interpret potentially user-generated, untrusted content from Bknd API endpoints (e.g., GET/POST to /api/data/:entity such as curl http://localhost:7654/api/data/posts, the /api/media/:path file endpoints, and the discoverApi script), exposing it to indirect prompt injection risk.