nemo-rl-session-memory

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill utilizes local shell commands such as mkdir, date, ls, and git for legitimate state management and repository inspection.
  • [SAFE]: The skill implements a session recovery workflow that includes mandatory sanitization: agents are instructed to verify claims against the git state and command output rather than blindly trusting the session files. Ingestion points (e.g., handoff.md) are handled with a 'verify-before-acting' policy.
  • [SAFE]: The instructions explicitly forbid the storage of secrets, tokens, or private credentials in session files, effectively mitigating credential exposure risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 07:42 PM
Security Audit — agent-trust-hub — nemo-rl-session-memory