google-chat

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly instructs the agent to call chat.getMessages and chat.listThreads (and to read thread messages) which fetches user-generated Google Chat content that the agent is expected to interpret and can directly influence subsequent actions like sending replies or creating threads, creating a clear path for indirect prompt injection.