understand-memory-sync

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs expected operations for a development utility, syncing project entities to a Memory MCP server.
  • [SAFE]: The skill processes untrusted local data from .understand-anything/knowledge-graph.json. While it lacks explicit boundary markers or sanitization, its operations are restricted to memory storage, representing a minimal attack surface. Ingestion points: .understand-anything/knowledge-graph.json. Boundary markers: None. Capability inventory: mcp__memory__create_entities, mcp__memory__create_relations, and mcp__memory__add_observations in SKILL.md. Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 12:08 PM
Security Audit — agent-trust-hub — understand-memory-sync