Security & AI safety

Vulnerability scanning & code security

466 agents · most starred first

Vulnerability scanning & code security, page 3 of 5

mythosharness★ 19

Mythos-class autonomous vulnerability discovery from any strong coding model (Opus 4.7, GPT-5.5, DeepSeek V4, Gemini). Long-running, email-driven, self-distills skills, mutates its own code.

brin-cli★ 18

the credit score for context.

hermes-bumblebee-bridge★ 18

Read-only supply-chain scanning for Hermes Agent, powered by Perplexity's Bumblebee. Daily scans, Telegram alerts, JARVIS narration.

sec-check★ 17

Probably the most SKILLed security agent. Scan untrusted code for red flags before you run it—exfiltration, reverse shells, backdoors, and supply‑chain traps.

KinGAidra★ 17

An AI-powered extension for Ghidra that enhances analysis.

Critikal★ 16

Autonomous smart contract security research agent — finds and proves exploits via LLM-driven recon, hotspot mapping, and Foundry PoC generation.

argus★ 16

An open-source AppSec agent that reasons like an analyst: real scanners, your org's context, and a conversation instead of 400 findings.

Rampart★ 16

Open-source, self-hostable AppSec agent that finds, proves, and helps fix web/API vulnerabilities — evidence-first (independent validation, proof-of-exploit over CVSS lists) behind a deterministic allowlist→scope→risk→policy→audit safety pipeline. Bring your own LLM or run fully local.

AuPM★ 16

npm-compatible registry that crowdfunds supply chain security: donors pay auditors and maintainers in USDC on Algorand via x402

claude-audit★ 16

Command-line code auditor: fast static checks, plus an optional audit where Claude investigates the code with read-only tools.

sbom_analysis_using_agentic★ 15

Using AI Agents for Audit SBOMs for OSS Compliance

vscode-chonky★ 15

🍣 Chonky - A Superhuman LLM Auditing Agent for Solidity

MIESC★ 14

Multi-layer Intelligent Evaluation for Smart Contracts — 50 security tools across 35 analysis modules, 9 defense layers, one command. Pre-audit triage for Ethereum (EVM); multi-chain on the roadmap.

ai-graph-engineering-supplychain★ 13

Graph engineering for software supply-chain exposure: which CVE, through which dependency path, and the safe fix, with the path as proof. Zero-LLM graph construction, deterministic alerting.

krineon★ 12

Krineon: multi-agent, evidence-driven vulnerability-research harness

chain-guard★ 11

🛡️ AI-powered smart contract security auditing platform — multi-agent vulnerability scanning, risk scoring, gas optimization, and audit reporting powered by Xiaomi MiMo

xref-9b★ 11

llama.cpp gguf qwen qwen3 qwen3.5 cybersecurity

GhAIdra★ 10

AI assisted tools for Ghidra. Azure OpenAI, DeepSeek, Anthropic Claude, Ollama.

michael-security-agent★ 10

Michael Adams — security specialist agent for Claude Code with persistent memory, STRIDE threat modeling, and OWASP framework mappings.

index★ 10

Vet a package before your AI coding agent uses it — authoritative facts (CVEs, license, maintenance) via an MCP server + CLI. Local, no account.

model-alpha★ 10

Solidity contract auditor: bundled JavaScript call-graph extractor (@solidity-parser/parser) plus a stdlib Python CLI that POSTs each function to a Model Alpha audit endpoint.

Rev-Core★ 10

⚡ Autonomous reverse engineering engine & Model Context Protocol (MCP) server for binaries and applications in Systems Rust

PatchBench★ 10

PatchBench: Evaluating AI Agents for Vulnerability Patching https://arxiv.org/pdf/2609.04075

hexvero★ 10

Know what changed inside your Electron release: diff two builds for IPC, preload, windows, fuses and hosts, with file:line. CLI, CI gate, MCP server.

Corvus★ 10

MCP server and CLI for reverse engineering and security analysis of .NET and native binaries (PE, ELF, Mach-O): decompile, search, compare builds, patch. IDA and Ghidra optional.

aibom★ 9

An AI-BOM visual viewer

bv-mcp★ 9

DNS, email-authentication, TLS and exposure scanning for AI agents: 81 MCP tools, scored 0–100. Source-available (BUSL-1.1).

kc-secure-repo-template★ 9

Security-hardened GitHub repository template, designed to prevent supply-chain attacks. Includes vulnerability scanning and AI agent skills.

PureAutoCodeql★ 9

Multi-agent CodeQL vulnerability analysis pipeline for CVE research, source/sink tracing, query generation, and path selection.

resolve★ 9

Automated vulnerability triage and zero-day remediation of software at scale

AegisAl★ 9

AegisAl:基于 Tauri 2、FastAPI 与 LangGraph 的跨平台桌面安全智能体

npm-safe★ 9

Local-first npm supply-chain security scanner: static + optional LLM analysis, CLI/CI gates, desktop app, and AI-agent skills.

MCP-Sentinel★ 9

PortunusMCP Sentinel: build-time security scanning for MCP servers.

software-protection-skill★ 9

AI 写好了软件,授权怎么保护?从公开破解案例反推卡密、激活码、离线许可证与联网验证设计。Vendor-neutral Agent Skill for software licensing, license key validation, offline activation, device binding & anti-tampering reviews.

michael-security-agent★ 8

Michael Adams — security specialist agent for Claude Code with persistent memory, STRIDE threat modeling, and OWASP framework mappings.

secure-sdlc-agents★ 8

A team of Claude Code sub-agents that enforce security across the full SDLC, from ASVS requirements and threat modelling to SAST triage, IaC review, compliance attestation and release sign-off. Drop into any project. No security team required.

infynon-cli★ 8

Security-first Rust CLI for dependency risk scanning, API workflow testing, and shared coding memory.

llm★ 8

Advanced CVE Retrieval and Analysis using LLMs

anti-crack-skill★ 8

Claude Code 技能:客户端软件全维度防破解安全审计(7大通用维度 × 9个平台专项)

spotlight★ 8

Autonomous AI security engineer — multi-agent swarm that scans, exploits, fixes, verifies, and attests. Open source (Apache 2.0).

chennai★ 8

chennai (chen N ai) is a hybrid AI agent and a terminal user interface for static analysis, data-flow tracing, and AI-assisted code and security analysis.

genpark-bytecode-disassembler-instruction-auditor-skill★ 8

GenPark AI Agent Skill - Python bytecode disassembler analyzing opcode sequences, jump offsets, and security hot-spots to prevent arbitrary unsafe execution.

safe-pkgs★ 7

Package safety checks for AI agents before install via MCP

Sclawhub★ 7

🦞🛡️ Security scanner for OpenClaw AI agent skills

vulnerability-scanner-UniXcoder-RAG★ 7

AI-powered browser-based vulnerability scanner using UniXcoder embeddings and RAG with LLM to detect security flaws across 9 languages.

appsec-skills★ 7

Production-ready AI AppSec skills for SAST, threat modeling, remediation, PR security review, and serialization abuse analysis.

agentic-api-sentry★ 7

A .NET 8 tool that acts as a static, mission-bound agent to evaluate any OpenAPI 3 specification for governance and compliance readiness. It performs spec linting, basic security checks, rate-limit header detection, and safe endpoint sampling, then generates Markdown and JUnit reports for developers and CI/CD pipelines.

greprules★ 7

CLI & Agent plugin for fetching SAST rule packs from greprules.io and scanning local code changes.

enterprise-readiness-skill★ 7

Agent Skill for enterprise readiness assessment - security, quality, and automation | Claude Code compatible

secflow-knowledge-security-assistant★ 7

原生 macOS AI 安全智能体:漏洞情报、知识图谱、多语言代码审计与报告交付 | SwiftUI + FastAPI + LangGraph

phantom★ 6

Phanton: A lightweight ARP scanner for quick discovery of IoT devices on local networks. With experimental LLM packet analysis and vulnerability research

ave★ 6

AVE - Agentic Vulnerability Enumeration. The behavioral classification standard for agentic AI components.

Aura_AI_Scan★ 6

docker mcp-server-track region:us

misconfiguration-detection-skill★ 5

A skill for AI agents to perform misconfiguration detection powered by CoGuard.

x-engine★ 5

AI-Powered Code Review for Move Smart Contracts

security-audit★ 5

Universal security scanning skill for AI agents - finds hardcoded secrets, API keys, and vulnerabilities in any codebase. 60 regex rules (46 GitLeaks-informed secret patterns, 14 OWASP Top 10 checks) plus 15 dangerous-file checks. Markdown/SARIF/JSON reports. Works across Claude Code, Cursor, Windsurf, and any agentic platform.

sigil★ 5

Automated security auditing CLI for AI agent code — quarantine-first workflow for repos, packages, and agent tooling

xbow-validation-benchmarks-statistics★ 5

An interactive analytics dashboard designed to visualize the difficulty distribution, vulnerability coverage, and structural diversity of the Xbow benchmark suite.

Kuzushi★ 5

Kuzushi — Agentic SAST scanner with AI triage

mcp-server★ 5

Apiiro Guardian Agent

GRC-Mapping-Analyst★ 5

GRC Mapping Analyst is a NIST IR 8477-based toolkit for AI-assisted cybersecurity crosswalks, producing deterministic set-theory mappings (equal, subset_of, superset_of, intersects_with, not_related) and 12-column STRM CSV outputs across frameworks, regulations, and control catalogs.

solana-agent-scanner★ 5

Autonomous AI agent for scanning Solana programs for security vulnerabilities

learn-codex-workshop★ 5

Hands-on workshop: wire Codex CLI to SonarQube Cloud for secrets scanning, issue detection, and automated verification of AI-generated code

BurpHunterTK★ 5

AI-Powered Burp Suite extension for elite bug bounty hunting. Detects HIGH/CRITICAL vulnerabilities using LLMs.

sast-triage★ 5

AI-powered triage for SAST findings.

Cadence★ 5

Analyze suspicious commits via code patterns, velocity anomalies, and statistical markers. Scan websites for AI generated text using pattern detection and optional OpenAI validation.

pocmap★ 5

MCP-native CVE, PoC & exploit discovery toolkit (Metasploit, Nuclei, GitHub & more)

n8n-ai-agent-security-lab★ 5

CSINT Research side project for static and staging-safe security regression checks of n8n AI workflows.

supply-chain-hardening★ 5

Supply-chain payloads run at install, import, or repo-open time. Copy-pasteable hardening playbooks, zero-dep audit scripts, and an incident watch list for all three moments — npm, PyPI, crates.io, Go, CI/CD, and AI agent workspaces.

secure-code-auditor★ 5

Backend security Agent Skill that helps AI audit code, detect vulnerabilities, and generate secure-by-default backend applications, with deep Django/DRF coverage and guidance for any backend stack.

seizu★ 5

A security graph reporting tool, with agentic workflows, AI chat assistant, and automation for CVE remediation and graph data population.

AutoRE-CLI★ 5

Static-only binary analysis CLI and Agent Skill with bounded, evidence-backed output

pluto-ai★ 5

AI-Powered Code Security Analyzer. Pluto is a powerful CLI tool that uses AI to detect security vulnerabilities in your code.

VigilAgent★ 5

Security auditing CLI for AI-agent-authored code changesets: detects package hallucinations, indirect prompt injection, and AI-specific code defects before they hit production.

solidity-security-audit-skill★ 5

AI agent skill for Solidity smart contract security auditing

AuditSym★ 5

AuditSym -Offline-first GRC platform with integrated AI for NIST CSF 2.0, ISO 27001, CIS Controls v8, and COBIT audits. Features a Remediation Hub for findings management: priority matrix (Impact vs. Effort), full lifecycle tracking (open → assigned → in_progress → pending_validation → closed), treatment decisions .

AgentSec★ 5

Lightweight, local-first security testing command-line tool (CLI) built in Rust that scans LLM wrappers, RAG databases, and autonomous AI agents for OWASP Top 10 vulnerabilities

pi-ghidra★ 5

Autonomous headless Ghidra 12 reverse engineering for Pi, omp, and MCP clients: decompile, xrefs, call graphs, strings, memory, and patches without the GUI.

clauderabbit★ 5

ClaudeRabbit is a free, open-source security product protecting the open-source community from malware. We clone any public GitHub repo into an isolated sandbox, run it, and return one honest safety score.

lorikeet-security-exporter★ 5

Agentic exporter and runner for internal network pentesting, autonomous host discovery, patch/vulnerability state collection, and server/application inventory, surfaced as structured findings for the Lorikeet Security platform.

rugsnare★ 5

218 silent contract changes found in the npm MCP top. Pin MCP tool contracts, fail CI on drift. Zero deps, no telemetry, on-chain verified.

ai-repo-safety-skill★ 5

Guardrails and security scanning for AI/vibe-coded repos: secrets, SAST, supply chain, git hooks

vulnrag★ 5

Cross-project vulnerability intelligence system. Aggregates CVEs from multiple databases with source code, indexes them as vector embeddings, and retrieves patterns across projects and languages.

auggiesec-agent★ 4

AI-powered security scanner that analyzes codebases for OWASP Top 10 2021 vulnerabilities with full observability via Langfuse.

haveibeenclawned★ 4

Security audit for OpenClaw agents — 72 checks, one command

should-i-care★ 4

Should you care about this CVE? An agent skill that triages whether a CVE applies to your environment, with sourced, verifiable reasoning.

EvoNet-AI-Core★ 4

Autonomous AI Security Agent leveraging LLMs, RAG, and Knowledge Graphs for automated CVE analysis and auto-patching.

auditforge★ 4

Multi-agent Smart Contract Security Audit Pipeline — 5 specialized AI agents for vulnerability scanning, logic auditing, gas analysis, compliance checking, and report generation. Powered by MiMo.

EllipticZero★ 4

Source-available local multi-agent engine for smart-contract security review and defensive ECC research with reproducible evidence. FSL-1.1-ALv2.

Port-Scanner-Vulnerability-Assessment★ 4
sovereign-rag★ 4

Sovereign, local, offline RAG for code auditing

breachproof★ 4

Autonomous AI security agent that audits, pentests, and hardens your whole codebase: SAST, secrets, SCA, IaC, containers, CI/CD, OWASP, and AI/LLM red-teaming. Auto-fixes vulnerabilities and maps findings to compliance frameworks like SOC 2. Works with Claude Code, Cursor, Codex, and opencode.

safety-copilot★ 4

streamlit region:us

Nova-Qwen2.5-14B-Secure-Coder★ 4

transformers safetensors gguf qwen2 text-generation code

nsauditor-ai-agent-skill★ 4

AI Agent Skill for NSAuditor AI — gives any AI coding agent built-in knowledge of NSAuditor's MCP tools, schemas, plugins, and security audit workflows. Works with Claude Code, Cursor, Windsurf, and any MCP-aware agent.

cwe-skills★ 4

AI-native CWE (Common Weakness Enumeration) integration layer — Skills, Go SDK, CLI & MCP. Ship CVE/CWE tooling to SAST/DAST, vuln-management & AI agents.

actenon-scan★ 4

Find where agent-controlled intent reaches consequential actions without an authority check. Python + TypeScript + Go. Zero-dependency SAST for AI agents.

lacuna★ 4

Agentic C/C++ vulnerability scanner powered by Claude. Autonomously reviews code, analyzes git history, and fuzzes with AFL++/libFuzzer — all inside a network-isolated Docker sandbox.

ghostpkg★ 4

Catch AI-hallucinated package names before you install them

argus★ 4

Agentic multi-agent framework for autonomous LLM vulnerability discovery: CVSSv4.0 scoring, 8-framework compliance mapping, SARIF output. OWASP LLM Top 10 (2025).

More in Security & AI safety