Caveat verdict
video-to-text
video-to-text-2
This skill transcribes videos from Bilibili, YouTube, and local files using bilibili-api and yt-dlp with faster-whisper, standard tools for the stated video-to-text conversion purpose.
โ Flagged for review โ coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis โ not a human review. Caveat 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 โ requests elevated privileges
SKILL.md ยท code ยท sudo
yum install โ installs system packages
SKILL.md ยท code ยท yum install
pip3 install โ installs Python packages at runtime
SKILL.md ยท code ยท pip3 install
subprocess execution โ runs system commands from Python
scripts/video_to_text.py ยท prose ยท downgraded ยท subprocess.run(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution โ cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions โ minimal attack surface.
network_outpackage_install Is this flag fair?
Thanks โ recorded.