hermes-integration
Warn
Audited by Snyk on Apr 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly lists Hermes MCP tools like messages_read and attachments_fetch that ingest user-generated content from platforms (Telegram/Discord/Slack) and describes using that conversation data to create/refine skills and drive decisions, exposing the agent to untrusted third-party content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata