cognee-custom-graph-models
Warn
Audited by Snyk on Oct 5, 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 skill describes defining custom knowledge graph models for Cognee, where text passed via
cognee.remember(text)is processed by the LLM, representing user input ingestion.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata