gmail

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

• Third-party content exposure detected (high risk: 0.90). This skill fetches and decodes arbitrary user-generated email content from Gmail API endpoints (e.g., https://gmail.googleapis.com/gmail/v1/users/me/messages/{message-id} and attachments endpoints), exposing the agent to untrusted third-party content that could contain injected instructions.