@tank/gmail

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 ingests email message bodies/threads fetched via the Gmail API (e.g., users.messages.get / users.threads.get), which are authored by external correspondents rather than the operating user, creating an indirect prompt-injection path through the message text.