by XiaoYiWeio · Codex Skill · ★ 70
DeepSafe Scan AI Agent 环境通用安全预检扫描器 📖 完整文档与演示 → xiaoyiweio.github.io/deepsafe-scan 运行前先扫描。一条命令,保护你的 AI Agent 环境免受密钥泄露、提示词注入、Hooks 后门攻击。 想了解这些攻击是怎么运作的?→ AI Agent Attack Techniques ⚡ 攻击者只需 3 秒,就能从你的 AI Agent 环境中窃走 SSH Key、API Key 和全部敏感凭证。 ↓ 真实攻击演示(3 倍加速) · 观看完整原速视频 → 你 clone 的下一个仓库,可能已经在等你打开它了。 <
| Stars | 70 |
| Forks | 10 |
| Language | Python |
| Category | Codex Skill |
| Quality Score | 60.3319014554319/100 |
| Last Updated | 2026-05-29 |
| Created | 2026-03-05 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~141k |
These tools work well together with deepsafe-scan for enhanced workflows:
Explore other popular codex skill tools:
deepsafe-scan is Universal preflight security scanner for AI coding agents — Detects hooks injection, credential exfiltration & backdoors in .cursorrules, CLAUDE.md, AGENTS.md and more.. It is categorized as a Codex Skill with 70 GitHub stars.
deepsafe-scan is primarily written in Python. It covers topics such as ai-agents, aisecurity, claude.
You can find installation instructions and usage details in the deepsafe-scan GitHub repository at github.com/XiaoYiWeio/deepsafe-scan. The project has 70 stars and 10 forks, indicating an active community.