add-matrix

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md and Channel Info explicitly wire the agent to Matrix rooms (e.g., "Invite the bot to a Matrix room and send a message" and "typical-use: Interactive chat"), meaning the agent will ingest and act on untrusted, user-generated content from public Matrix homeservers which could influence its actions.