synapse
Warn
Audited by Snyk on Jun 12, 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). At runtime, the SDK’s
discover()andrequest()primitives ingest JSON envelopes received over NATS (e.g.,mesh.registry.discoverreplies andmesh.agent.{id}.inboxresponses) into the agent’s in-memory context; those messages can be authored by other agents (outsider) and include free-formpayload/outputtext.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata