multi-agent-chat

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly requires the agent to read and act on messages from multi-user channels (Discord/Slack/Teams or any shared channel) that contain user-generated, potentially untrusted content, so those incoming messages (see SKILL.md "Use this skill when you are an AI agent in a channel with other AI agents and human participants") could indirectly inject instructions affecting agent behavior.