gmail-automation

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow for this Gmail skill calls scripts/gmail.py to fetch email message bodies/headers from the user’s Gmail account via the Gmail API; those email contents are authored by third parties (outsiders) and become readable prose in the agent context when the skill returns “full message content” or headers.