email-forensics

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

• Third-party content exposure detected (high risk: 0.90). The skill's Link Analysis features (e.g., extract/unshorten_urls and analyze_destinations with "safe fetch"), plus the THREAT_INTEL_FEED/URL-based verification and the note "URL analysis requires network access for verification", indicate the agent will fetch and interpret arbitrary external URLs extracted from emails (untrusted public third-party content).