Caveat verdict

model-usage

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

Local CodexBar CLI wrapper that reads local cost log JSON and summarizes per-model usage; the execution sink is the codexbar CLI invocation, all processing is local, and no external network calls are made beyond the local CLI tool.

⚠ 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.

60
security
100
transparency
70
maintenance

Findings (2)

Pattern match critical

Pipe to python — executes piped content as Python code

SKILL.md · code · | python

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 D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

Requires 1 system binary.

Is this flag fair?

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