wonderchat

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and run actions against Wonderchat (e.g., "membrane action run --connectionId=... ACTION_ID" and "membrane request CONNECTION_ID /path/to/endpoint"), which will retrieve user-generated conversation/message content from the public third-party service that the agent is expected to read and act on, so untrusted third-party content could inject instructions affecting subsequent actions.