Caveat verdict

Car Search

car-search

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

The skill runs local Python scripts via uv to aggregate used-car listings from Chinese platforms and presents results to the user; all operations are local data aggregation for the stated purpose with no suspicious behavior.

⚠ 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.

48
security
90
transparency
70
maintenance

Findings (3)

Pattern match critical

Pipe to python — executes piped content as Python code

dev_docs/STEPS.md · code · | python3

Pattern match high

<script> tag in markdown — potential code injection

dev_docs/AGENTS.md · prose · downgraded · <script

Pattern match low

Python os.environ.get — reads environment variable

scripts/car_cli/commands/export.py · prose · downgraded · os.environ.get(

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