retrieve-memory

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a memory retrieval workflow that includes explicit security guidance. It instructs the AI to treat external data as informational ('data-not-instruction blocks') and identifies a non-bypassable 'holdback' mechanism designed to suppress high-risk or low-trust content from the agent's context. No malicious patterns or unauthorized behaviors were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 03:03 AM
Security Audit — agent-trust-hub — retrieve-memory