gmail

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly reads and interprets users' email content from Gmail (see read_email, get_email_thread, list_emails, search_emails in SKILL.md), which can contain arbitrary, untrusted user-generated text that could influence replies, sends, deletions, or other agent actions.