mailsac

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

• Third-party content exposure detected (high risk: 0.90). This skill retrieves and displays user-generated emails and their bodies from public Mailsac endpoints (e.g., https://mailsac.com/api/addresses/{email}/messages and /api/body/{email}/{messageId}), so the agent ingests arbitrary third-party content that could carry indirect prompt injection.