email-forensics

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow ingests and parses user-supplied email evidence files (e.g., /evidence/suspicious.eml, /evidence/mailbox.pst), and the LLM context would therefore include the email body/headers authored by third parties (outsider email senders/participants) as readable text during analysis.