security-scanner

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.

Bandit is a tool designed to find common security issues in Python code.

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。

A high performance offensive security tool for reconnaissance and vulnerability scanning

Source Code Security Audit (源代码安全审计)

A security tool for multithreaded information gathering and service enumeration whilst building directory structures to store results, along with writing out recommendations for further testing.

GitHub Sensitive Information Leakage（GitHub敏感信息泄露监控）

🆕 The Multi-Tool Web Vulnerability Scanner.

Semi-automated, feedback-driven tool to rapidly search through troves of public data on GitHub for sensitive secrets.

A default credential scanner.

A modular vulnerability scanner with automatic report generation capabilities.

Enumeration sub domains(枚举子域名)

A python2 script for sweeping a network to find windows systems compromised with the DOUBLEPULSAR implant.

A friendly car security exploration tool for the CAN bus

Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.

Offensive security platform that automates attack surface discovery and vulnerability management

OXO is a security scanning orchestrator for the modern age.

Burp-Automator: A Burp Suite Automation Tool with Slack Integration. It can be used with Jenkins and Selenium to automate Dynamic Application Security Testing (DAST).

Searches through git repositories for high entropy strings and secrets, digging deep into commit history

Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.