graph-engineer
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data related to graph entities and Cypher queries, which presents a potential surface for indirect prompt injection. However, the skill provides comprehensive defensive guidance to mitigate this risk.
- Ingestion points: User-provided entity names, relationship descriptions, and Cypher query requests processed by the agent.
- Boundary markers: The SKILL.md file explicitly directs the agent to ground all responses in specific reference files and to prioritize those patterns over generic user requests.
- Capability inventory: The skill facilitates the generation and optimization of Cypher queries for graph databases like Neo4j and FalkorDB.
- Sanitization: The reference files (
references/sharp_edges.mdandreferences/validations.md) contain explicit instructions to avoid string concatenation and use query parameterization to prevent injection vulnerabilities.
Audit Metadata