neo4j-graph-data-scientist
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill instructions encourage the agent to write and execute ad-hoc scripts using external libraries such as
pytorch,scikit-learn,pandas, andmatplotlibto perform complex data science tasks. This involves the runtime generation and execution of code within the agent's environment. - [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting data from external Neo4j databases through Cypher queries and GDS tools (referenced in
SKILL.md). This creates an attack surface where malicious content stored in the database could attempt to influence the agent's behavior. - Ingestion points: Data retrieved from Neo4j databases via the
gds-agentandmcp-neo4j-cyphertools. - Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions embedded within the database results.
- Capability inventory: The agent is granted the capability to write and execute Python scripts and perform database operations.
- Sanitization: There are no documented procedures for sanitizing or validating the data returned from the database before it is processed or used in script generation.
Audit Metadata