
defenseclaw
Security Governance for Agentic AI

Security Governance for Agentic AI

Isolated Docker lab and static scanner for CVE-2025-55182, with vulnerable/patched Next.js builds and PoC validation of RSC Flight deserialization.

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。

Unified security scanner for MCP servers with config, pentest, and repo-scan modes. Generates SARIF reports for CI/CD integration, detects secrets,…

Docker labs + defensive scanner for fastjson remote-class-load RCE. fastjson 1.2.66-1.2.83: @JSONType resource probe (CVE-2026-16723). fastjson2…

Educational PoC + lab for CVE-2026-63030 + CVE-2026-60137: pre-auth SQLi in WordPress core via REST batch-route confusion

🔐 CVE-2026-57821 - Apache Fineract SQL Injection Toolkit 📚 Two Python scripts for authorized security testing: verifier.py (safe detection, no…

CVE-2026-53753 — Crawl4AI <0.8.7 unauthenticated RCE (AST sandbox escape via gi_frame.f_back). Lab + PoC, verified e2e.

Reproducer for CVE-2026-40048: Apache Camel camel-pqc FileBasedKeyLifecycleManager unsafe deserialization (RCE)

Maintained fork of node-ip with the unpatched SSRF advisory (CVE-2024-29415) fixed

AI-powered vulnerability scanner extension for Burp Suite with multi-provider support (Ollama, OpenAI, Claude, Gemini)

Host-agnostic pre-write security hook for coding agent: detects user-input patterns via Semgrep and emits deterministic, no-LLM security guidance.

AI-powered SAST scanner that finds auth bypass, IDOR, and logic bugs Semgrep/CodeQL miss. Free GitHub Action. Supports Python, JS/TS, Go, PHP, Ruby.

Benchmark measuring AI models' ability to detect vulnerabilities in source code via real bug bounty cases with balanced recall and false-positive…

Using Struts2 and PowerShell to recreate CVE-2017-5638 OGNL Injection vulnerability.