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 JuneYaooo · Codex Skill · ★ 83
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is self-media-compliance-review safe to install? View the security audit →
self-media-compliance-review 自媒体视频发布前的违规风险审核 Skill。 适用于 Claude Code / Codex / OpenClaw / Hermes 等支持 Skills 的 agent。把它装进 agent 后，可以在短视频、切片、封面、标题、字幕、口播、商品链接和发布文案交付前，按本仓库整理的参考规则做一遍结构化风险审核。 它不是“敏感词表”，而是一套面向发布前质检的审核流程：会检查画面、声音、文字、封面、评论引导、带货信息、资质、授权、引流和平台常见风险，并给出具体修改建议。 也欢迎大家在 Issues 里提供各平台规则资料、审核经验、踩坑案例和整改思路。后续会不定期整理进这个 skill。 能做什么 按平台读取参考文件：根据目标平台读取视频号、微信公众号、抖音、快手、B站、小红书的规则参考。 电商合规审核：商品三一致检查（视频 vs 详情页 vs 口播）、千川低质素材避坑、功效声明核验、行业资质排查、价格/赠品/活动一致性。 覆盖常见发布面：检查脚本、封面、标题、字幕、口播、画面、BGM、评论、商品链接和账号资料。 风险分级：输出 / / / / 。 证据定位：要求标注视频时间点、字幕行、封面文案、商品链接或待核验证据。 修改建议：给出消音、打码、删改、补资质、补授权、改写话术、移除链接等具体动作。 案例排查参考：对限流、封号、申诉、原创争议、评论灰产等场景给出排查方向和申诉材料清单。 本地证据检索：默认可用，只搜索随 Skill 发布的规则和案例文件，不联网、不消耗 API 额度，并返回可追溯的文件和行号。 实时平台证据（可选）：仅在用户明确要求实时搜索时，通过当前环境已有的 TikHub、平台浏览插件/Skill 或浏览器工具检索近期案例和讨论。 隐形规则补充：除官方规则外，整理了各平台创作者实际发布和评论区讨论中的经验样本，用来补充官方没写明的隐形审核尺度（作为症状和争议线索，不当作平台规则）。 机器可读输出：支持 JS
| Stars | 83 |
| Forks | 9 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 57.6843171362155/100 |
| Last Updated | 2026-09-19 |
| Created | 2026-06-19 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~15k |
These tools work well together with self-media-compliance-review for enhanced workflows:
Looking for a self-media-compliance-review alternative? If you're comparing self-media-compliance-review with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
103 ready-to-use AI agent skills for Claude Code, OpenAI Codex, Gemini CLI, Cursor, GitHub Copilot, Windsurf,
Bring Agent Skills to Any AI Agent and Coding Agent — via CLI or MCP. Manage once, serve anywhere.
AI agent skills for social media content strategy, creation, and analysis across text-first platforms
Marketing frameworks that AI actually executes. Designed for Claude Code, but could be used for OpenClaw, etc.
Modular plugin marketplace for Claude Code and agentic CLIs, with validated, spec-driven skills, agents, comma
Terraform Skill for Claude Code and Codex. LLMs hallucinate a lot with Terraform - TerraShark fixes this. It e
Explore other popular codex skill tools:
self-media-compliance-review is 自媒体视频发布前违规风险审核。检查画面/声音/文字/封面/评论/带货信息/资质/引流，输出 Pass→Blocker 五级风险报告。覆盖抖音/小红书/视频号/B站/快手+千川低质素材。Claude Code、codex、workbuddy、hermes skill. It is categorized as a Codex Skill with 83 GitHub stars.
self-media-compliance-review is primarily written in Python. It covers topics such as ai-agent, ai-agents, claude-code-skills.
You can find installation instructions and usage details in the self-media-compliance-review GitHub repository at github.com/JuneYaooo/self-media-compliance-review. The project has 83 stars and 9 forks, indicating an active community.
self-media-compliance-review is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to self-media-compliance-review on Agent Skills Hub include awesome-ai-agent-skills, skillport, social-media-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: