Caveat verdict
video-prompt-reverse
This skill downloads short videos, extracts key frames with ffmpeg, and analyzes them via Doubao using CDP browser automation to produce structured video prompts, behavior matches stated purpose of reverse-engineering video prompts.
⚠ 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
package_install
Findings (4)
Pipe to python — executes piped content as Python code
references/full_workflow.md · prose · downgraded · | Python
subprocess execution — runs system commands from Python
references/full_workflow.md · code · subprocess.run(
HTTP request to bare IP address — common in malicious payloads
scripts/cdp_client.py · prose · downgraded · http://127.0.0.1
Opens WebSocket connection
references/full_workflow.md · prose · downgraded · websocket
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.
package_install Is this flag fair?
Thanks — recorded.