mcp-neo4j-memory-ops
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill processes data from a Neo4j database which acts as an untrusted ingestion point.
- Ingestion points:
SKILL.md(Node retrieval via fuzzy match). - Boundary markers: Absent; no instructions provided to treat retrieved data as non-executable text.
- Capability inventory:
SKILL.md(UsesMCP(*)allowing any MCP tool call). - Sanitization: Absent; no validation or escaping of retrieved graph data is specified.
Audit Metadata