botstar

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

• Third-party content exposure detected (high risk: 0.80). Yes — SKILL.md explicitly instructs the agent to fetch Botstar data via Membrane commands (e.g., "membrane action run" for actions like list-entity-items/get-user and "membrane request CONNECTION_ID /path/to/endpoint"), which ingests third‑party/user-generated content from the Botstar platform that the agent is expected to read and could materially influence subsequent actions.