analyzing-email-headers-for-phishing-investigation

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests untrusted, user-generated email messages (EML files) as part of its required workflow—see SKILL.md Step 1 (examples copying/using /cases/.../phishing_email.eml) and scripts/agent.py which parses EMLs, extracts email body/URLs/attachments and uses those contents to drive DNS/API checks and phishing indicators—so third-party content can materially influence analysis and subsequent tool use.