munity

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md describes accessing Munity community data (user-generated "Community" posts/members) via Membrane actions and the proxy request flow (e.g., "membrane action list/ run" and "membrane request CONNECTION_ID /path/to/endpoint"), so the agent will fetch and read third-party user-generated content from Munity that could influence subsequent actions.