loomio

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and proxy requests to Loomio's API (e.g., "membrane request CONNECTION_ID /path/to/endpoint" and using membrane action run to read Discussions/Comments/Polls), which are user-generated, third‑party Loomio posts and thus could be ingested and influence subsequent actions.