agentmail
Warn
Audited by Snyk on Jul 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). Outsider-authored free text can enter the LLM context via
agentmail inboxes:threads getreturningmessages[].text/extracted_textfrom inbound emails (untrusted mail from other senders), which the recipes then parse for links/codes.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata