agent-teams

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

• Third-party content exposure detected (high risk: 0.90). The skill reads and processes user-generated Microsoft Teams content (e.g., agent-teams snapshot, message list, snapshot --full, and templates/monitor-channel.sh and common-patterns.md) and includes workflows that parse message content and automatically respond or take actions, so untrusted third-party messages can materially influence agent behavior.