neo4j-vector-index-skill
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill documents standard Neo4j Cypher syntax and procedures for vector indexing. All provided examples follow best practices, such as using parameters ($openaiKey, $NEO4J_PASSWORD) instead of hardcoded secrets.
- [EXTERNAL_DOWNLOADS]: The skill references standard Python libraries (
neo4j,openai) and provides an installation command targeting the vendor's official GitHub repository (neo4j-contrib), which is consistent with the skill's purpose. - [INDIRECT_PROMPT_INJECTION]: The skill illustrates the use of
LOAD CSVfor data ingestion inSKILL.md. While this represents an ingestion point for external data, it is a standard feature for vector indexing tasks and is presented as a generic usage template. - Ingestion points:
LOAD CSVcommand inSKILL.md(Cypher-Based Embedding Ingestion section). - Boundary markers: None explicitly defined in the generic Cypher example.
- Capability inventory: Database property updates (
SET), vector searches (SEARCH,queryNodes), and embedding generation viaai.text.embed. - Sanitization: Not included in the simplified code examples.
Audit Metadata