talamus-memory
Warn
Audited by Snyk on Jul 21, 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). The required runtime workflow uses
talamus ingest PATH_OR_URL/talamus scan .which can read outsider-authored public web content or uploaded repository files into Talamus’s indexing and (for retrieval/synthesis steps liketalamus ask --trace) feed that retrieved free text back into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata