GitHub repo leaderboard by stars, growth rate and activity.

• NVIDIA

  #1NVIDIA/SkillSpector

  Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.

  Python16,801 starslast pushed Yesterday
• superagent-ai

  #2superagent-ai/superagent

  Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.

  TypeScript6,737 starslast pushed 2 weeks ago
• Tencent

  #3Tencent/AI-Infra-Guard

  A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

  Python6,215 starslast pushed 24 hours ago
• protectai

  #4protectai/llm-guardArchived

  The Security Toolkit for LLM Interactions

  Python3,204 starslast pushed 2 months ago
• tldrsec

  #5tldrsec/prompt-injection-defenses

  Every practical and proposed defense against prompt injection.

  —731 starslast pushed 2 years ago
• Tcotl

  #6Tcotl/AgentCapture

  嵌入式蜜罐与 AI Agent 反制平台：23 种 Agent 指纹识别 + 功能性伪装收编 + 对话式 C2 + 交互式 SSH 蜜罐与会话回放，实测五款主流 Agent 全部反制上线。

  Python74 starslast pushed 7 days ago
• Yuxuan2003

  #7Yuxuan2003/Awesome-GUI-Agent-Security

  GUI / Computer-Use / Browser Agent 安全论文清单 —— 按攻防轴组织，每篇附中文简介

  Python67 starslast pushed 7 days ago
• aimeoa

  #8aimeoa/hanshuang-codex

  针对GPT 5.6,V4flash的破甲实验项目

  Python61 starslast pushed 2 days ago

#	Repo	Language	Stars	30-day trend	Last updated
1	NVIDIA NVIDIA/SkillSpector Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.	Python	16,801		last pushed Yesterday
2	superagent-ai superagent-ai/superagent Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.	TypeScript	6,737		last pushed 2 weeks ago
3	Tencent Tencent/AI-Infra-Guard A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.	Python	6,215	—	last pushed 24 hours ago
4	protectai protectai/llm-guardArchived The Security Toolkit for LLM Interactions	Python	3,204		last pushed 2 months ago
5	tldrsec tldrsec/prompt-injection-defenses Every practical and proposed defense against prompt injection.	—	731		last pushed 2 years ago
6	Tcotl Tcotl/AgentCapture 嵌入式蜜罐与 AI Agent 反制平台：23 种 Agent 指纹识别 + 功能性伪装收编 + 对话式 C2 + 交互式 SSH 蜜罐与会话回放，实测五款主流 Agent 全部反制上线。	Python	74		last pushed 7 days ago
7	Yuxuan2003 Yuxuan2003/Awesome-GUI-Agent-Security GUI / Computer-Use / Browser Agent 安全论文清单 —— 按攻防轴组织，每篇附中文简介	Python	67		last pushed 7 days ago
8	aimeoa aimeoa/hanshuang-codex 针对GPT 5.6,V4flash的破甲实验项目	Python	61	—	last pushed 2 days ago

All · 11,474