Caveat verdict

tmd-wangda

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

A skill for automating course learning on China Mobile training platform managing progress via local session files with no unusual data exfiltration beyond the stated learning automation purpose.

⚠ 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.

23
security
90
transparency
70
maintenance

Findings (7)

Pattern match high

Dynamic Function constructor — equivalent to eval()

scripts/stealth-extension/stealth.js · prose · downgraded · new Function(

Pattern match high

Function.prototype.constructor access — indirect eval

scripts/stealth-extension/stealth.js · prose · downgraded · Function.prototype.constructor

Pattern match high

Uses eval() — can execute arbitrary code

scripts/stealth-extension/stealth.js · prose · downgraded · eval(

Pattern match medium

subprocess execution — runs system commands from Python

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

Pattern match low

Opens WebSocket connection

references/tools.md · prose · downgraded · websocket

Pattern match low

Python urllib.request — network access

scripts/chrome_tools.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

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

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

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