ClawAudit verdict
triple-layer-memory
Three-layer memory management system using local files and Mem0 for cross-session recall; agent_memory capability is used as intended for memory management, no external data exfiltration.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
agent_memory
Findings (4)
References SSH/GPG private keys
docs/github-upload-guide.md · code · ssh-key
Accesses .ssh directory
docs/github-upload-guide.md · code · .ssh/
References agent memory files
SKILL.md · code · MEMORY.md
Accesses OpenClaw config/secrets directly
scripts/memory_consistency.py · prose · downgraded · ~/.openclaw/openclaw.json
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
agent_memory Is this flag fair?
Thanks — recorded.