Skills/ClawHub/h3-video-editing-prompt

h3-video-editing-prompt@1.0.1

VERIFIED

Publisher claims: "Write or revise MiniMax H3 Ref2VA prompts for editing a source video from reference images or audio, especially masked or false-colour person replacement, face replacement, costume or object replacement, cross-shot identity persistence, overlay cleanup, and lip-sync preservation. Use when a request" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher wangminrui2022 · joined 0 days agoInstalls 501Last detonated 2 h ago
$clawhub install h3-video-editing-prompt
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 93/100 (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
0.0sprocessno install scripts to re-run

Static findings

No findings across 902 lines in 7 files.

Cost to the agent

Instructions loaded
≈4,068 tok
1 file · 7 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.

h3-video-editing-prompt@1.0.1 safety verdict: Verified 93/100 — KillerSkills