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 xiaoTN · Codex Skill · ★ 78
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is zelda-style-image-prompt safe to install? View the security audit →
Codex Skills Collection 这个仓库用于开源和维护 Codex Skill。每个 skill 放在 下。 当前包含： ：生成塞尔达原版游戏实况截图风格的图片提示词 ：面向 macOS Codex Desktop 的“海拉鲁旷野”独立主题安装包 安装 先克隆仓库： 安装到全局 Codex skills： 或安装到当前项目： 安装后重启 Codex，让 skill 被重新扫描。 使用 在 Codex 里直接提出需求： skill 会输出可直接交给图片生成模型的最终提示词代码块。 声明 本仓库的 skill 部分只包含提示词写作规则和参考文档，不包含游戏原始模型、字体、音频或任天堂官方资源。 是 AI 生成的同人主题背景，不属于任天堂官方素材，也不包含在仓库 MIT 软件许可的授权范围内；具体说明见该主题目录的 。 本项目与 Nintendo、The Legend of Zelda、Breath of the Wild、Tears of the Kingdom 或其权利方没有关联、授权、赞助或背书关系。项目中出现的游戏名称、角色名称和商标仅用于描述提示词风格与兼容场景。 使用本仓库中的 skill 生成、发布或商用任何内容时，请自行确认是否符合相关平台规则、模型服务条款和知识产权要求。 License MIT
| Stars | 78 |
| Forks | 15 |
| Language | Shell |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 55.2168973067685/100 |
| Last Updated | 2026-08-23 |
| Created | 2026-05-31 |
| Platforms | cli, codex |
| Est. Tokens | ~11k |
Explore other popular codex skill tools:
zelda-style-image-prompt is Codex Skill for writing Zelda-style image prompts. It is categorized as a Codex Skill with 78 GitHub stars.
zelda-style-image-prompt is primarily written in Shell.
You can find installation instructions and usage details in the zelda-style-image-prompt GitHub repository at github.com/xiaoTN/zelda-style-image-prompt. The project has 78 stars and 15 forks, indicating an active community.
zelda-style-image-prompt is released under the MIT license, making it free to use and modify according to the license terms.
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: