molted
Warn
Audited by Snyk on Nov 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required read/react workflow (
read_inbox/GET /v1/agent/threads,get_thread,classify_inbound, and the SSE/webhook inbound feed) ingests inbound email from arbitrary external senders, and any outsider can email a mailbox the agent reads without the agent first selecting an item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata