ClawAudit verdict
openclaw-security-handbook-cn
Comprehensive security audit guide running local diagnostics and interactive fix workflows; all operations are user-confirmed and no data is sent externally without consent.
⚠ 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 (8)
Recursive delete from root or home — destructive command
references/fix-commands.md · code · rm -rf ~
Accesses OpenClaw config/secrets directly
SKILL.md · code · ~/.openclaw/openclaw.json
References child_process — can spawn system processes
references/checklist.md · code · child_process
References sudo — requests elevated privileges
references/fix-commands.md · code · sudo
References agent memory files
SKILL.md · code · MEMORY.md
Opens WebSocket connection
references/checklist.md · code · WebSocket
Sets world-executable permissions
references/fix-commands.md · code · chmod 700
subprocess execution — runs system commands from Python
scripts/security-report.py · prose · downgraded · subprocess.run(
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.
agent_memory Is this flag fair?
Thanks — recorded.