neo4j-aura-graph-analytics-skill
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from Neo4j databases and CSV files, which represents an indirect prompt injection attack surface.\n
- Ingestion points: Data enters the context via
pd.read_csvfor node and edge files and through remote graph projections from Neo4j databases as shown inSKILL.mdandreferences/workflows.md.\n - Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious instructions embedded within the ingested data.\n
- Capability inventory: The skill utilizes file system access for data loading, network operations for database connectivity, and environment-based package installation.\n
- Sanitization: No explicit data sanitization or validation steps for the content of the graphs or CSVs are included in the patterns.\n- [EXTERNAL_DOWNLOADS]: The skill references and fetches resources from official Neo4j domains and repositories.\n
- Fetches configuration and guidance from
neo4j.comdocumentation.\n - References tutorial notebooks and examples from the official
neo4j/graph-data-science-clientGitHub repository.
Audit Metadata