ClawHub

Vpick Ai Video Creator

v1.0.1

All-in-one AI video production studio on a visual canvas. Generate videos (Kling 3.0, Veo 3.1, Sora 2, Runway, Grok, Midjourney Video), generate images (nano...

⭐ 0· 54·0 current·0 all-time
by@snoopyrain
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name/description (AI video studio) match the runtime instructions: all actions are calls against the VPick service (canvas/project/node operations, generation, upload, export). Nothing in the SKILL.md requires unrelated credentials, binaries, or system access.
ℹ
Instruction Scope
Instructions stay within the VPick production workflow (create/list canvas, add nodes, generate media, combine/export). However, the skill explicitly instructs sending user prompts and uploaded media to VPick, which then forwards them to third‑party model providers — a privacy/data‑sharing consideration rather than an incoherence.
✓
Install Mechanism
No install spec or code is included (instruction-only), so nothing is downloaded or written to disk by the skill itself.
✓
Credentials
No environment variables, local API keys, or config paths are requested by the skill. Authentication is handled by the MCP connector URL (not listed as an env var), which is proportionate to a cloud-hosted service integration.
✓
Persistence & Privilege
The skill does not request always:true or other elevated persistence. Autonomous invocation is allowed by default (platform normal), and there is no indication the skill modifies other skills or system-wide settings.
Assessment
This skill delegates all work to the VPick cloud. Before installing or connecting: (1) treat your MCP link as a secret (it grants generation/manage rights in your account) and do not paste it into public chats; (2) review VPick's privacy and billing policies — prompts and uploaded media are sent to VPick and relayed to third‑party model providers; (3) avoid uploading sensitive personal or proprietary data unless you accept that it will be processed by VPick and external models; (4) prefer testing with a throwaway account/limited credits first; (5) verify the VPick domain and service reputation independently (and rotate/regenerate the MCP token if you suspect misuse).

Like a lobster shell, security has layers — review code before you run it.

latestvk9708656f8yt117ar8chqxp6r583rvkm

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Runtime requirements

🎬 Clawdis

Comments