Caveat verdict

umeng-push-helper

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

Read-only push analytics skill that uses user-provided browser cookies to query upush.umeng.com; explicitly prohibits write operations and only performs the stated read-only monitoring queries.

⚠ 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.

25
security
90
transparency
70
maintenance

Findings (6)

Pattern match critical

Possible hardcoded credential

COOKIE_VALIDATION_UPDATE.md · code · token=' not in cookie_value: return False,

Pattern match high

<script> tag in markdown — potential code injection

scripts/query_msg_detail.py · prose · downgraded · <script

Pattern match medium

subprocess execution — runs system commands from Python

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

Pattern match medium

subprocess with shell=True — command injection vector

scripts/query_msg_detail.py · prose · downgraded · subprocess.run(['start', filepath], shell=True

Pattern match low

Python urllib.request — network access

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

Pattern match low

References webhook/callback URL

scripts/query_daily_api_stats.py · prose · downgraded · CallbackUrl

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