mailsac

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and read emails from public inboxes (e.g., /api/text, /api/body, /api/raw and the "List Messages in Inbox" and "Wait for Email and Extract Verification Code" examples), which are untrusted, user-generated third-party content that the skill processes and uses to drive actions.