Caveat verdict
video-analyzer
This skill downloads and transcribes Bilibili/YouTube videos using standard tools (yt-dlp, Whisper, FFmpeg) and analyzes them via a configured LLM provider, all consistent with its stated video analysis 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.
Permission integrity
credential_access
agent_memory
Findings (8)
Possible hardcoded credential
README.md · code · token="your_parent_node_token
References sudo — requests elevated privileges
README.md · code · sudo
subprocess execution — runs system commands from Python
dependency_manager.py · prose · downgraded · subprocess.run(
yum install — installs system packages
dependency_manager.py · prose · downgraded · yum install
Downloads executables from external URLs
dependency_manager.py · prose · downgraded · Download from https://
Python urllib.request — network access
feishu_publisher.py · prose · downgraded · urllib.request
Python os.getenv — reads environment variable
feishu_publisher.py · prose · downgraded · os.getenv(
Python shutil file operation — copies/moves/deletes files
main.py · prose · downgraded · shutil.copy(
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.
agent_memorycredential_access Is this flag fair?
Thanks — recorded.