ClawAudit verdict

model-usage

token-usage-dashboard

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

Reads local CodexBar CLI cost JSON files and summarizes per-model usage; all operations are local with no network calls or credential access.

⚠ 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.

40
security
90
transparency
70
maintenance

Findings (3)

Pattern match critical

Pipe to python — executes piped content as Python code

SKILL.md · code · | python

Pattern match high

<script> tag in markdown — potential code injection

scripts/test_token_usage_dashboard.py · prose · downgraded · <script>

Pattern match medium

subprocess execution — runs system commands from Python

scripts/model_usage.py · prose · downgraded · subprocess.check_output(

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