ClawAudit verdict

clawseccheck

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Local read-only security self-audit tool that explicitly states it makes no network calls, never modifies OpenClaw setup, and only writes private local reports; a transparent defensive inspection tool.

⚠ 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.

0
security
100
transparency
90
maintenance

Findings (19)

Pattern match high

Pipe to sh — executes piped content as shell commands

README.md · prose · downgraded · |sh

Pattern match high

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

README.md · prose · downgraded · curl http://<ip> | bash

Pattern match high

Pipe to bash — executes piped content as shell commands

README.md · prose · downgraded · | bash

Pattern match medium

Accesses OpenClaw config/secrets directly

clawseccheck/collector.py · prose · downgraded · ~/.openclaw/openclaw.json

Pattern match medium

Instructs covert action — may act without user awareness

clawseccheck/coverage.py · prose · downgraded · silently

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

clawseccheck/dryrun.py · prose · downgraded · http://198.51.100.7

Pattern match medium

subprocess execution — runs system commands from Python

clawseccheck/native.py · prose · downgraded · subprocess.run(

Pattern match medium

Accesses system credential store

clawseccheck/report.py · prose · downgraded · keychain

Pattern match medium

Uses exec() — may execute shell commands

clawseccheck/risk.py · prose · downgraded · exec (

Pattern match medium

Accesses .ssh directory

clawseccheck/skillast.py · prose · downgraded · .ssh/

Pattern match medium

References sudo — requests elevated privileges

docs/FAQ.md · prose · downgraded · sudo

Pattern match low

References agent memory files

clawseccheck/attest.py · prose · downgraded · MEMORY.md

Pattern match low

Python os.environ.get — reads environment variable

clawseccheck/cli.py · prose · downgraded · os.environ.get(

Pattern match low

Popular HTTP library — network access

clawseccheck/collector.py · prose · downgraded · got

Pattern match low

Sets world-executable permissions

clawseccheck/risk.py · prose · downgraded · chmod 700

Pattern match low

Blob URL — may embed executable content

clawseccheck/sar.py · prose · downgraded · blob:

Pattern match low

Python urllib.request — network access

clawseccheck/skillast.py · prose · downgraded · urllib.request

Pattern match low

Changes file ownership

docs/FAQ.md · prose · downgraded · chown

Pattern match low

References agent configuration files

docs/OUTPUT_SCHEMA.md · prose · downgraded · CLAUDE.md

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/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?

Check another skill Browse the registry Auditing your own skills or configs? Use the API