hermes-runtime
Warn
Audited by Snyk on Aug 21, 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 hermes-runtime skill ingests outsider-authored free text directly from the user-provided CLI arguments into the required workflow “chat” (and “run”) via
hermes-companion.mjs chat <message>→cmdChat→api.chat/streamChat(POSTing that text into Hermes), and also forwards Hermes-returned content back to the caller verbatim.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata