memory-layer

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill manages data within the local .agents/memory/ directory and utilizes a local memory router. No patterns of data exfiltration or unauthorized network requests were found during the analysis.
  • [COMMAND_EXECUTION]: The skill uses Bash and Grep to search through session notes in its own data directory. These operations are scoped to local files and do not involve untrusted input execution.
  • [SAFE]: A mandatory Human-In-The-Loop (HITL) checkpoint is implemented for all 'WHY-tier' promotions, ensuring the AI cannot commit permanent project decisions to long-term memory without explicit user approval.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 09:04 AM
Security Audit — agent-trust-hub — memory-layer