sota-architecture
Warn
Audited by Snyk on Jun 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). JetStream consumer/workflow runtime ingests message payloads (outsider-authored free text) into the agent’s LLM context via the JetStream message handler path, which can contain arbitrary text from external producers; this is an indirect prompt-injection vector.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata