gmail

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly lists and retrieves Gmail mailbox content via Membrane actions (e.g., "List Messages", "Get Message", "Get Thread" in SKILL.md), meaning the agent will fetch and read user-generated email content from users' Gmail accounts which could contain untrusted instructions that influence its actions.