hermes
Warn
Audited by Snyk on Jun 29, 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). Inbound platform/webhook events are received by
hermes::inbound(HTTP) and then republished into the iii worker context, so outsider-authored free-form message bodies/comments from external users can be ingested by the agent at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata