Caveat verdict

token-safety-checker

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Local security tool scanning openclaw.json for plaintext secrets; explicitly documents that secret values are never passed as CLI args, never logged, and never appear in agent context.

⚠ 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.

8
security
90
transparency
70
maintenance

Findings (6)

Pattern match high

Accesses OpenClaw config/secrets directly

SKILL.md · code · ~/.openclaw/openclaw.json

Pattern match high

Accesses shell history/config

SKILL.md · code · ~/.zshrc

Pattern match high

Pipe to bash — executes piped content as shell commands

README.md · prose · downgraded · | bash

Pattern match high

Pipe to sh — executes piped content as shell commands

README.md · prose · downgraded · | sh

Pattern match medium

subprocess execution — runs system commands from Python

scripts/safeclaw.py · prose · downgraded · subprocess.run(

Pattern match low

Python os.environ.get — reads environment variable

scripts/safeclaw.py · prose · downgraded · os.environ.get(

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