Skills/ClawHub/video-animate

video-animate@1.0.1

VERIFIED

Publisher 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: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher vargai · joined 9 days agoInstalls 35Last detonated 2 h ago
$clawhub install video-animate
WatchReport an issue

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-06 and scored it 82/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only

Static findings

LOW
Refusal suppressionreferences/models.md:109 · Refusal suppression — attempting to prevent safety responses · informational: not an instruction fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentREADME.md:1 · HTML comment carrying imperative instructions to the agentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Python subprocess execution detectedscripts/take_check.py:28 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈5,233 tok
1 file · 18 in bundle

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.