spice-connect-data

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests open, user-generated third‑party content (e.g., the "github:github.com/.../issues" connector and the "https://url/path/data.csv" HTTP/HTTPS connector) and exposes that content as tables/documents the agent is expected to read and query, enabling indirect prompt injection.