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 sukai213 · Codex Skill · ★ 6
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is bilibili-ai-video safe to install? View the security audit →
AI 科技测评视频制作与 B 站自动发布技能（Codex Skill）：原创文案 / Qwen3-TTS 配音 / 全息幻灯片 / ffmpeg 剪辑 / 投稿 API 自动发布
| Stars | 6 |
| Forks | 3 |
| Language | Python |
| Category | Codex Skill |
| Quality Score | 53.9163150416477/100 |
| Last Updated | 2026-08-07 |
| Created | 2026-08-06 |
| Platforms | codex, python |
| Est. Tokens | ~13k |
Explore other popular codex skill tools:
bilibili-ai-video is AI 科技测评视频制作与 B 站自动发布技能（Codex Skill）：原创文案 / Qwen3-TTS 配音 / 全息幻灯片 / ffmpeg 剪辑 / 投稿 API 自动发布. It is categorized as a Codex Skill with 6 GitHub stars.
bilibili-ai-video is primarily written in Python.
You can find installation instructions and usage details in the bilibili-ai-video GitHub repository at github.com/sukai213/bilibili-ai-video. The project has 6 stars and 3 forks, indicating an active community.
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: