Caveat verdict
qcut-toolkit
This is a media toolkit skill routing to sub-skills for FFmpeg processing, AI content generation, and editor control; all capabilities are consistent with legitimate local media workflow orchestration.
⚠ 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.
Findings (6)
HTTP request to bare IP address — common in malicious payloads
qcut-mcp-preview-test/SKILL.md · code · http://127.0.0.1
<script> tag in markdown — potential code injection
videocut/subtitles/scripts/subtitle_server.js · prose · downgraded · <script>
References child_process — can spawn system processes
videocut/subtitles/scripts/subtitle_server.js · prose · downgraded · child_process
Uses spawn() — can execute external programs
videocut/subtitles/scripts/subtitle_server.js · prose · downgraded · spawn(
References agent configuration files
videocut/self-evolve/SKILL_CN.md · prose · downgraded · CLAUDE.md
Node http/https module — low-level network access
videocut/subtitles/scripts/subtitle_server.js · prose · downgraded · require("http")
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?
Thanks — recorded.