assist-gmail

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

• Third-party content exposure detected (high risk: 0.85). Outsider free text can enter the LLM context via the server’s Gmail triage/analysis path: scripts/gmail-axi triage / triage progress triggers AI analysis of synced emails (message subject/body and other email text authored by external senders), which the server then feeds into the LLM.