ClawAudit verdict

voice-mode

45
🟠 Risky
Significant concerns — only install if you understand the risks

The skill hardcodes a real Telegram Bot Token (8790428866:AAHqdKyvZGTB26Deg79HoCZTuiAiTsvwWzs) and Chat ID directly in the SKILL.md, meaning any agent loading this skill gains the ability to send messages to that Telegram account without additional authorization, and the token is exposed to anyone reading the skill.

⚠ 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.

83
security
70
transparency
70
maintenance

Findings (4)

Pattern match medium

subprocess execution — runs system commands from Python

voice_daemon.py · prose · downgraded · subprocess.run(

Pattern match low

Python urllib.request — network access

voice_daemon.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

voice_daemon.py · prose · downgraded · os.environ.get(

Pattern match low

Python http.client — stdlib network access

voice_daemon.py · prose · downgraded · http.client.HTTPSConnection

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