ClawAudit verdict

openclaw-model-switch

openclaw-model-switch-2

45
🟠 Risky
Significant concerns — only install if you understand the risks

The skill switches and adds AI models using natural language, which could potentially be used maliciously.

⚠ 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.

68
security
90
transparency
90
maintenance

Findings (4)

Pattern match medium

Accesses OpenClaw config/secrets directly

SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json

Pattern match medium

subprocess execution — runs system commands from Python

scripts/add-model-guide.py · prose · downgraded · subprocess.run(

Pattern match medium

os.system/popen — direct OS command execution

scripts/switch-model.py · prose · downgraded · os.system(

Pattern match low

Python shutil file operation — copies/moves/deletes files

scripts/switch-model.py · prose · downgraded · shutil.copy(

Why the tier is capped

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