Vulnerability scanning & code security
466 agents · most starred first
Vulnerability scanning & code security, page 2 of 5
REVLab - Windows PE reverse engineering workflow platform (static analysis, unpacking, disassembly, decompile, dynamic sandbox, network capture, custom pipelines, MCP + AI agent integration). For lab/legal compliance testing only.
Offline security scanner for AI-agent repos, skills, plugins, and MCP servers.
RAG/LLM Security Scanner identifies critical vulnerabilities in AI-powered applications, including chatbots, virtual assistants, and knowledge retrieval systems.
An AI hacker for Web3 Smart Contract. for bug bounties, Audit contest, offensive security research, and real-world exploit thinking.
A highly flexible AI Agent-driven EVM smart contract vulnerability detection framework
Binary Ninja plugin to provide LLM assistance analyzing binaries.
Prototype of Full Agentic Application Security Testing, FAAST = SAST + DAST + LLM agents
Benchmark for evaluating LLM agents on smart-contract vulnerability discovery and exploitation
Vulnerability impact analyzer that reduces false positives in SCA tools by performing intelligent code analysis. Uses agentic AI with open source models to understand CVEs and verify actual vulnerability impact in your codebase. Keeps your code secure with on-premises execution and human-in-the-loop verification.
LLM-native static vulnerability detection: point it at a repo and get a reviewable vuln report, the way a human auditor would.
Claude Code / agentic security skill for Solana programs and software. Full audit-firm lifecycle, executable PoC + fix-patch delivery, a Rust pre-scanner + cross-audit memory, 1,346 checks across 20 checklists, and 131 real-world attack vectors.
A security-first MCP server empowering AI agents to orchestrate Ghidra, Radare2, and YARA for automated reverse engineering.
Subdosec is a fast, accurate subdomain takeover scanner with no false positives. It also offers a database of sites vulnerable to subdomain takeover (public results), along with detailed metadata like IP, CNAME, TITLE, and STATUS CODE for reconnaissance to identify potential new vulnerabilities.
Temodar Agent is an AI-powered WordPress plugin and theme security analysis platform built for security researchers, product security teams, auditors, and defenders. It combines AI agent workflows, multi-provider LLM orchestration, Semgrep-powered static analysis, and risk-based WordPress reconnaissance in one local-first Docker application.
LLM Agent Skill for YARA rule authoring and review
The system consists of multiple AI agents that collaborate to strategize, generate commands, and execute scans based on the client's description, without the need for human intervention.
AI powered web security testing for authorized targets
Open-source AI security scanner for Codex, Claude Code, and ACP-compatible coding agents—kept current with OpenAI Codex Security.
Agent Skill for PHP security audits - OWASP patterns, vulnerability detection | Claude Code compatible
CodeAuditSkill 是一个运行在 Claude Code 中的 Web 项目安全代码审计/漏洞挖掘 Skill, 已经获得了40余个CNVD漏洞编号。 给定一个 Web 项目目录,自动识别语言与框架,按语言专属漏洞清单进行系统化源码审计,对每条高中危漏洞并行启动子 Agent 进行可利用性验证,最终输出可交付的审计报告。
Sound static analysis and LLM reasoning, in one security agent
Deterministic Android unpacking pipeline for AI agents: zero-token mechanical analysis, LLM-outsourced bottlenecks, Rust-side verdicts.
Local-first MCP security scanner for AI-generated apps: four open-source engines plus the Synvoya engine. Scan → fix → rescan from Claude Code, Cursor, Codex, and other agents.
AI/ML and Generative AI Security Assessment Framework for AWS. Automatically audit Amazon Bedrock , SageMaker ,AgentCore, and Agent Registry workloads for security best practices
Open-source security audits for Supabase: a read-only MCP server, a CLI agent and a Claude Skill. Finds RLS misconfigurations, exposed keys and risky functions, and returns a scored report with fix SQL. Hosted version: Locksoup.
Purpose-built security agent for hosted runners
Vetix — Automated scanning, identification, and assessment of SKILL security risks, based on Golang.
[ICML 2026] Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks
AI-driven Dynamic Application Security Testing tool for security engineers. Combines an HTTPS MITM proxy with a multi-agent scanner and a real-time web dashboard. Route any browser or tool through the proxy — findings appear automatically.
Check your Mac with your coding agent after the October 2026 security incidents
Security Scan orchestrator for AI Agents 🎯
Skills and plugins to accelerate security workflows with the Orca Cloud Platform
The AI security agent guards your code.
Vibe CSA (Code Security Audit),是一款基于 AI Agent 架构的代码审计工具,采用多 Agent 并行执行架构,用“上帝视角”静态审计源代码,用“实战模拟”动态验证漏洞,保证了 Web 漏洞挖掘的全面性和准确性,输出稳定可靠的安全报告,并提供可落地整改建议。
Designed for managing vulnerability discovery at scale with agentic AI and integrates with HackerOne.
Generate CS2 signatures via Agent SKILLS with ida-pro-mcp
OSCAL tools for AI agents
Downloads for Mend's Unified Agent
An AI-powered security analysis tool for web applications that combines Large Language Model (LLM) analysis with intelligent agent-based verification to identify and validate security vulnerabilities in your codebase.
Outside-in replication of Anthropic's Mythos Preview / Project Glasswing — open-source agentic vulnerability-discovery scaffold on Claude Opus 4.7. Eight-phase sink-guided pipeline, ~$1/run, OSS self-scan and coordinated disclosure.
Agent skill for producing threat models for open-source projects
Black-box security assessment for live MCP servers.
Free XP on bug bounty, vulnerability scanning by wrapping well maintained tools, to perform automated tests. Alongside AI agents for binary analysis, which includes connecting to external Android or emulator to perform dynamic analysis.
Java Web 全链路自动化安全审计系统。基于 Claude Code Agent Teams,一行命令完成路由识别→调用链追踪→8种漏洞检测→利用链编排→审计报告。覆盖 SQL 注入/反序列化/SSRF/表达式注入/XXE/文件上传/文件读取/鉴权绕过 + OSV.dev 3000+ CVE。支持快速模式、增量审计、CFR 反编译。
20-pass adversarial audit for vibe-coded software. Injection, IDOR, races, N+1, idempotency, transactions, memory leaks — then a false-positive verifier.
A multi-agent application-security review harness for Claude Code (and, later, other AI agents). One router skill dispatches to a full offensive-security pipeline that maps a codebase, hunts vulnerabilities with a per-class knowledge base, chains findings into escalations, verifies real impact, and reports to README/JSON/SARIF/doc/PDF.
Lightweight BApp that seamlessly integrates powerful LLM-scanning capabilities into Burp's built-in Scanner with improved accuracy. Supports the latest LLMs from OpenAI (gpt-4o, o1), Anthropic (Claude 3.5, Claude 3), and Google (Gemini 1.5). Requires valid API key(s) and an active Burp Suite Pro or Enterprise license.
High-performance zero-dependency static analysis tool enforcing NASA Power of Ten rules across 20 programming languages, plus AI agent skill, MCP server config, prompt template, and LLM model security auditing.
Solana's SOL-0XX security standard — bug-class rules distilled from $514M of real exploits, firing as you code in every AI tool, editor & CI.
The official Rifteo agent skills library - a collection of reusable instruction sets for AI agents covering security testing, audit, and compliance workflows. Supports 53 agents
CVE ingestion + enrichment pipeline with an MCP server for AI agents.
Evidence-driven reverse engineering and unpacking workflows for AI agents, with reproducible Windows experiments.
docker agent-demo-track security mcp vulnerability-scanner ai-agent region:us
PoliteWebScanner is a learning-grade web vulnerability scanner plus AI-assisted report viewer. It crawls safely (queue-based, robots-aware, rate-limited), detects common issues (security headers, cookie flags, reflected XSS heuristics, SQL error patterns), and exports human-friendly JSON/HTML reports with optional AI help for triage and remediation
基于 LLM 的白盒漏洞挖掘 Agent。四条挖掘路径(启发式、快速扫描 Sink 回溯、历史漏洞绕过、无约束)+ Docker 靶场 / 局部 harness / 静态验证,支持互联网复现与攻击链串联。 LLM-based white-box vuln mining agent. Four paths (heuristic, fast-scan sink backtrace, historical bypass, unconstrained) + Docker lab / harness / static verify; Internet retest and attack chains.
LLM powered agents for scanning vulnerabilities on any website - Llama 3 8B, Groq, Selenium, CrewAI, Exa AI
Audit, clean, and harden a WordPress site end to end, with an AI agent (Claude/Cursor/Codex/MCP or SSH). Detects & removes hidden malware — cloaking, backdoors, database injection — scores your security posture, and hardens safely. Free, open-source (AGPL-3.0).
面向企业内部授权场景的 AI 代码安全审计框架。支持 redteam/full 两种模式,支持靶场集成验证,全程自动编排。适配 Cursor、Claude Code 及其他支持 Agent 调度的 AI IDE。
AI Agent for cost-efficient and trustworthy memory-safety vulnerability detection for large-scale codebases.
The Project shares all information on MCP related CVE's published
Static analysis and attack-surface scanner for AI agents — SAST for prompts, tools, MCP servers, and agent workflows. Detects capabilities, prompt risks, tool permissions, and governance gaps before deployment.
Security gate for AI-generated code - blocks the build until vulnerabilities are fixed
Agentic Framework for Synthesizing CodeQL Queries
Autonomous multi-agent CVE analysis on Android. No cloud. No GPU. No API key. MNN + Qwen in Termux. BLAKE3 tamper-proof logs. Config-driven. 300€ phone.
IVAgent (Intelligent Vulnerability Agent) 是一个基于大语言模型(LLM)的智能漏洞挖掘 Agent,支持多种分析引擎和二进制/源码分析场景。
The Polyspace Agentic Toolkit brings trusted Polyspace capabilities to AI agents.
Open-source security scanner for AI Agent skills, plugins & MCP servers. 39 detection rules. pip install prism-scanner
MCTS (Model Context Threat Scanner) is a local-first security scanner for MCP servers -- static and live tool discovery, multiple analyzers, auditable risk scores, and JSON, SARIF, and HTML output. For authors and platform teams; CI-ready, no cloud API.
Multi-language CLI for Rafter — the security toolkit built for AI coding agents and the developers who use them.
AI security agent for the Python supply chain: scans packages, generates exploits, and validates them in Docker, autonomously.
PHP framework to test User-Agents and intermediary content inspection devices for denial-of-service vulnerabilities with respect to HTTP response decompression.
Open security scanner and self-hosted control plane for AI, MCP, and cloud. One evidence model — scan locally, centralize findings, govern in your VPC.
VulnAgent is an experimental AI-assisted cybersecurity agent framework that orchestrates modular agents using LLMs and domain-specific tools, communicating over XMPP.
Agent-assisted vulnerability research across Rust, Android APKs, and AI agents: independent discovery, skeptical triage, verification, and patch review.
ZAST Express: Your Security Copilot in IDE.
Flutter APK/AAB security SKILL.md for OpenClaw, Codex, Claude Code, and other AI coding agents
Cybersecurity knowledge graph for code review with evidence-backed answers
AVE - Agentic Vulnerability Enumeration. The open behavioral classification standard for agentic AI components.
Security scanner for MCP servers. Grades auth, permissions, injection risks, and tool safety. The Lighthouse of agent security.
Find vulnerabilities. Ship secure. — Senior security-engineer skill for AI coding agents. OWASP Top 10, CWE Top 25, secrets detection, IaC + CI hardening, and a read-only auditor subagent. MIT.
An 8-stage AI vulnerability-discovery agent.
Dependency safety gate for Claude Code & Codex CLI — OSV pre-approval, npm lockfile-closure enforcement, and auto-rollback. Local, zero runtime deps.
Evidence-governed security compliance verification framework for IoT products, initially validated for ETSI TS 103 701 / EN 303 645. Connects test orchestration, traffic intelligence, traceable evidence, and independent review.
REA (Reverse Engineer Anything) in Docker: one image per analysis engine (Ghidra / Hopper / IDA) with a full reverse-engineering toolchain, MCP-ready for Hermes and other agents.
Reusable AI agent skills for AuditHub security tools. Teach Claude Code and Codex how to run OrCa fuzzing campaigns, launch DeFi Vanguard scans, and analyze findings. Plug and play.
One scan for AI risk. `opena2a review` checks an AI project across credentials, shadow agents, MCP servers, and dependencies, returns a score, and routes each finding to the tool that fixes it. Open source.
🥑 Inspect and understand an organization's software supply chain using AI to enable stakeholders to make actionable decisions about software supply chain security
Cloud security audit tools for AI agents — AWS, Azure, GCP misconfiguration detection via MCP. 38 tools, 60+ checks. The agent finds vulns, not you.
Agent-native code security review with MCP, structured findings, and practical pre-merge scanning workflows.
🎯 VISTA — AI-Powered Security Testing Assistant for Burp Suite. Real-time traffic analysis, 12 expert vulnerability templates, 80+ payloads, WAF detection & bypass. Supports OpenAI, Azure, and OpenRouter (FREE). Zero dependencies.
Self-hosted, agentic vulnerability research for binaries & firmware: an AI agent decompiles, fuzzes, and verifies exploits inside a sandbox, recording every finding to a typed graph. BYOK, fully local.
Scan Python dependencies for exploited CVEs and abandoned packages that handle untrusted input, ranked by CISA KEV and EPSS. Runs in CI and as a Claude Code hook.
Deterministic CI scanner and surface-risk scoring for MCP (Model Context Protocol) servers.
AI orchestration framework for structured multi-step workflows with validation - build reliable smart contract security analysis and beyond
A TypeScript package that provides AI-powered agents for Application Security (AppSec) tasks, built on top of the frontier models.
Vulnerability scanning with your own scanners and threat feeds, plus a coding agent that opens the fix PR. CLI, GitHub Action, or scheduled Managed Agents deployment.
Reverse engineering with AI agents on Windows: verifying, measuring and visualising the tools agents use, with rea and Ghidra
ebpf-based monitoring and vulnerability scanning tool for AI/ML workloads on Linux
An autonomous agentic pipeline that finds, proves, and patches real C memory-safety vulnerabilities end-to-end using a single 7B open-source LLM (Qwen2.5-Coder) on vLLM, with AddressSanitizer as a ground-truth oracle.