clip

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and interacts with arbitrary external endpoints (e.g., "clip add https://.../openapi.json", "clip add https://...mcp", GraphQL targets, and "clip refresh ") so untrusted third‑party schemas/responses are fetched and used to drive operations and behavior, enabling indirect prompt injection.