agora

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

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md instructs using the Membrane CLI to run Agora actions (e.g., recordings/transcripts via "membrane action run" and action list/get flows) whose output the agent is expected to read and act on, meaning it ingests user-generated third-party content (recordings/transcripts) that could contain instructions and influence subsequent decisions.