email-security

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs agents to resolve and follow shortened URLs and redirect chains and to evaluate the final destination of arbitrary external links found in inbound emails (see "URL validation", "Redirect chain analysis", "Shortened URL expansion" and the Implementation checklist), which requires fetching and interpreting untrusted third‑party web content that can materially influence link-safety decisions and agent actions.