agentmail
Warn
Audited by Snyk on Jul 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). SKILL.md describes webhook-driven processing where incoming email content (outsider-authored messages) is placed into the agent context via the webhook transform’s
text: ... ${payload.message.subject} ... ${payload.message.text}path.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata