video-animate@1.0.4
CAUTION· static onlyPublisher claims: "Animate a video once the previz, characters, moodboard, script and sound exist. Decide per element whether code, AI video or both makes it, pick Seedance 2.5 or another model per shot, run a cheap 480p pass before paying for quality, choose one long generation or short clips, roll takes that differ only in performance, cut picture to the locked track, and generate plates the next agent can add motion design to and edit. Built from working AI filmmakers, vendor guides, sync standards and the film and animation canon, with frame counts, prompts, a take checker and a database directory. Use for "animate my previz", "Blender to Seedance", "three.js to video", "grey box to video", "which model for this shot", "Seedance or Kling", "long take or short clips", "480p draft", "animate to the beat", "cartoon timing", "music video from my previz", "footage ready for motion design". Not for building the previz (threejs-animatic, varg-previz), making the sound (video-sound) or the final edit (varg-video-editing)." Observed in sandbox: static analysis only — behavior not yet observed.
Coverage
Static only; nothing was run yet.The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-12 and scored it 63/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: HTML comment carrying imperative instructions to the agent. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
return subprocess.run(cmd, capture_output=True, text=True, errors="replace")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.| When to stay on 2.0 | Never refused in Everypixel's 15 clips, against 3 refusals for 2.5 | | Use `seedance_2` only for a whole sequence that needs 4K, a cheaper tier or fewer refusals [inference] |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Generated by .github/readme/build.ts from SKILL.md files and .github/readme/*.json. Edit those and run `bun .github/readme/build.ts`; CI fails when this file isFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
17 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim vargai: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.