neo4j-graphrag-skill
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides guidelines for the
neo4j-graphragPython package, authored by the official community contributor (neo4j-contrib). - [SAFE]: Includes security mentions of a 'Destructive-query guard' in the
Text2CypherRetrieverwhich usesEXPLAINto prevent prompt-injection attacks from executing write/destructive statements (CREATE, DELETE, etc.). - [SAFE]: Encourages the use of environment variables for API keys and sensitive credentials rather than hardcoding them.
- [SAFE]: External dependencies (
neo4j-graphrag,langchain,weaviate-client,pinecone-client,qdrant-client) are standard industry libraries for graph databases and RAG workflows. - [SAFE]: Documentation neutrally references trusted and well-known services including OpenAI, Anthropic, Google (Vertex AI/Gemini), AWS (Bedrock), and various vector database providers.
Audit Metadata