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 (Uses MCP(*) allowing any MCP tool call).
  • Sanitization: Absent; no validation or escaping of retrieved graph data is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 11:21 AM