understand-coremind

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates in a read-only capacity, extracting information from a local JSON file to assist in project documentation.
  • [SAFE]: Analysis of the instructions confirms there are no attempts at prompt injection, obfuscation, or data exfiltration.
  • [SAFE]: The use of the mcp__memory__search_nodes tool is limited to searching architectural entities and is consistent with the skill's purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 01:25 PM
Security Audit — agent-trust-hub — understand-coremind