ClawAudit verdict
memory-optimizer-base
Multi-agent memory management system with local private/public knowledge spaces; the 'upload' command requires manual confirmation and appears to write to a local shared directory rather than an external server.
⚠ 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.
Findings (3)
os.system/popen — direct OS command execution
memory_optimizer.py · prose · downgraded · os.system(
References agent memory files
lib/summarizer.py · prose · downgraded · MEMORY.md
References agent configuration files
memory_optimizer.py · prose · downgraded · agent_config
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). 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.
Is this flag fair?
Thanks — recorded.