by lintsinghua · LLM Plugin · ★ 7.1k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
DeepAudit - 人人拥有的 AI 审计战队，让漏洞挖掘触手可及 🦸♂️ <p
| Stars | 7,108 |
| Forks | 857 |
| Language | Python |
| Category | LLM Plugin |
| License | AGPL-3.0 |
| Quality Score | 51.4843256779103/100 |
| Open Issues | 95 |
| Last Updated | 2026-10-01 |
| Created | 2025-09-19 |
| Platforms | gemini, python |
| Est. Tokens | ~19k |
Looking for a DeepAudit alternative? If you're comparing DeepAudit with other llm plugin tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to
📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for w
Open-source Next.js template for building apps that are fully generated by AI. By E2B.
Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs
The pretty much "official" DSPy framework for Typescript
Sim is the collaborative workspace to build, deploy, and monitor AI agents and workflows. Used by 100,000+ bui
Explore other popular llm plugin tools:
DeepAudit is DeepAudit：人人拥有的 AI 黑客战队，让漏洞挖掘触手可及。国内首个开源的代码漏洞挖掘多智能体系统。小白一键部署运行，自主协作审计 + 自动化沙箱 PoC 验证。支持 Ollama 私有部署 ，一键生成报告。支持中转站。让安全不再昂贵，让审计不再复杂。. It is categorized as a LLM Plugin with 7.1k GitHub stars.
DeepAudit is primarily written in Python. It covers topics such as ai, bug-detection, code-audit.
You can find installation instructions and usage details in the DeepAudit GitHub repository at github.com/lintsinghua/DeepAudit. The project has 7.1k stars and 857 forks, indicating an active community.
DeepAudit is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to DeepAudit on Agent Skills Hub include composio, repomix, fragments. 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: