ClawAudit verdict
bilibili-transcriber
The skill appears to be a legitimate tool for transcribing Bilibili videos, using cloud and local engines for transcription, and generating summaries. No clear malicious behavior or excessive capabilities are used.
⚠ 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.
Permission integrity
network_out
package_install
Findings (4)
References sudo — requests elevated privileges
SKILL.md · code · sudo
subprocess execution — runs system commands from Python
fast_transcribe.py · prose · downgraded · subprocess.run(
Python os.environ.get — reads environment variable
cloud_transcriber.py · prose · downgraded · os.environ.get(
Python urllib.request — network access
fast_transcribe.py · prose · downgraded · urllib.request
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D/F). 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.
network_outpackage_install Is this flag fair?
Thanks — recorded.