ai-gmail-inbox-classifier-auto-archive-with-hourly-telegram

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

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests free text from outsider-authored Gmail emails (fetches all inbox messages, then extracts full email body content and classifies it) via the required gmail-all-email-actions tool, so poison text can be delivered by the email sender into the inbox.