viral-video-decomposer — security grade SAFE, quality 62/100

Security audit verdict: SAFE · quality 62/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by sharon-laicc · Claude Skill · ★ 6

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is viral-video-decomposer safe to install? View the security audit →

About viral-video-decomposer

拆解爆款短视频,生成镜头级拉片、爆款机制、AI 生产蓝图和视频生成 brief 的 Codex/Claude skill。|A Codex/Claude skill for decomposing hot short videos into shot-by-shot analysis, reusable production blueprints, and AI-ready video generation briefs.

Quick Facts

Stars6
Forks0
LanguagePython
CategoryClaude Skill
LicenseMIT
Quality Score61.9348458681498/100
Last Updated2026-06-12
Created2026-06-05
Platformsclaude-code, codex, python
Est. Tokens~14k

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is viral-video-decomposer?

viral-video-decomposer is 拆解爆款短视频,生成镜头级拉片、爆款机制、AI 生产蓝图和视频生成 brief 的 Codex/Claude skill。|A Codex/Claude skill for decomposing hot short videos into shot-by-shot analysis, reusable production blueprints, and AI-ready video gener. It is categorized as a Claude Skill with 6 GitHub stars.

What programming language is viral-video-decomposer written in?

viral-video-decomposer is primarily written in Python.

How do I install or use viral-video-decomposer?

You can find installation instructions and usage details in the viral-video-decomposer GitHub repository at github.com/sharon-laicc/viral-video-decomposer. The project has 6 stars and 0 forks, indicating an active community.

What license does viral-video-decomposer use?

viral-video-decomposer is released under the MIT license, making it free to use and modify according to the license terms.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Claude Skill tools