Caveat verdict
claw-audit
This is a legitimate security scanning and hardening tool for OpenClaw that runs local scripts to detect malicious patterns, audit configuration, and calculate security scores; all commands are local node/bash scripts with no evidence of 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. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (10)
Accesses sensitive system files
PROJECT.md · code · /etc/shadow
Pipe to bash — executes piped content as shell commands
SKILL.md · prose · downgraded · |bash
References sudo — requests elevated privileges
PROJECT.md · code · sudo
Pipe to sh — executes piped content as shell commands
references/malicious-patterns.json · prose · downgraded · |sh
Pipe to python — executes piped content as Python code
references/malicious-patterns.json · prose · downgraded · |python
Bash /dev/tcp — raw TCP connection via shell
references/malicious-patterns.json · prose · downgraded · /dev/tcp/
Accesses .ssh directory
references/malicious-patterns.json · prose · downgraded · .ssh/
Accesses system credential store
references/malicious-patterns.json · prose · downgraded · keychain
References agent memory files
SKILL.md · prose · downgraded · MEMORY.md
References tunneling service
PROJECT.md · prose · downgraded · ngrok
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 2 system binaries.
Is this flag fair?
Thanks — recorded.