Security & AI safety

Vulnerability scanning & code security

466 agents · most starred first

Vulnerability scanning & code security, page 5 of 5

semgrep-agent
snyk-agent-scan

Agent supply chain security scanner.

sys-scan-agent

AI-powered intelligence layer for the sys-scan-graph security scanner.

trusys-llm-scan

A Python-based code scanning tool for AI/LLM-specific vulnerabilities

Amplify Security

Get instant, automated fixes for code security flaws.

@socketsecurity/mcp

Socket MCP server for scanning dependencies

Delve

AI-powered tool to automate security compliance and pass audits quickly.

agentgg

Agentic SAST scanner — white box, CI-ready, multi-provider. Reasoning where regex falls short.

dirtyfrag
agentsentinel-cli

AI agent and MCP server security scanner — discovery, static analysis, supply chain audit, and multi-agent trust analysis

agentvuln

AI Agent Security Scanner — detect tool-calling vulnerabilities in LLM agents

aegis-sb

Supabase security guardian — audits a Supabase project for the security holes that ship by default when AI builds your app

agentfort

CVE-style advisory database and static scanner for AI agent security risks

opensec-intelligence

Local-first, multi-agent AI security scanner. Finds vulnerabilities. Writes the patches. Free forever.

agentsec-scanner

Local-first security scanner for AI Agent, MCP, and AI coding tool projects.

mujin-agentaudit

Security & quality audit for AI-agent extensions (Claude Code skills, MCP servers, plugins) — scan before you install.

ragsec

Static security scanner for RAG pipelines

@appthreat/chennai

Interactive terminal UI for exploring AppThreat atom files with AI agent

@leo-agent/cli

Autonomous security auditing CLI — multi-agent LLM-powered vulnerability scanner

langchain-quantumscan

QuantumScan tools for LangChain, LangGraph, CrewAI, and AutoGen — pre-transaction safety checks and post-quantum cryptography scanning for autonomous agents.

shadowcat-agent

AI-powered autonomous web security scanner with real-time streaming — enterprise DAST platform

argus-scan

Argus CLI — multi-agent security oracle. Scan any token address from your terminal.

agentguardp

AgentGuard — AI Code Security Scanner + Auto-Fixer

ubuntu-sec-agent

面向 Ubuntu 的安全检测/加固/防护 skill,供 Claude Code / Codex 等 AI agent 调用,支持 npm/npx。命令:scan / run / status / harden / prune / fw-log / fw-rules / fw-optimize / fw-plan / fw-monitor / fw-verify / sensor-setup / sensor-collect / sensor-status / sensor-tune / correla

barrikade-lens

Local-first autonomous agent discovery for endpoints, repositories, and organizations

rakshakai

RakshakAI — AI-powered security scanner & chat. Scan 20+ languages, 150+ vulnerability patterns, 65+ AI models across 9 providers, multi-agent swarm, offline regex engine.

argus-redteam-agent

Argus RedTeam local security scan agent — code never leaves your infrastructure

argus-redteam-scan-agent

Argus RedTeam local security scan agent — code never leaves your infrastructure

depmirage

Spot AI-hallucinated and slopsquatting Python dependencies, typosquats, and hardcoded secrets.

graphrag-codeproperty-graph

Code Property Graphs — Joern/Semgrep extraction, AI vulnerability enrichment, risk scoring

owasp-audit-agent

Agentic AI framework untuk audit keamanan kode Python berbasis OWASP Top 10 (2025).

remy-agent

AI-Powered Codebase Bug & Vulnerability Scanning CLI

urllm

URL technical footprint analyzer with GDPR & security-focused GenAI reasoning

deepsec

AI-powered vulnerability scanner for any codebase

control-coverage

Control-first coverage and blind-spot analysis over an evidence corpus, with a Statement of Applicability.

dexllm

LLM-facing DEX/APK analyzer — pybind11 wrapper around DexKit Core with an embedded DAD-aligned Java decompiler, MCP server, and FastAPI/SSE backend

llm-security-tester

Automated vulnerability scanner for applications that integrate Large Language Models, covering the OWASP Top 10 for LLMs.

mseep-snyk-agent-scan

Agent supply chain security scanner.

s2n-agent

LLM-powered decision layer for the S2N web vulnerability scanner

@putervision/spc

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.

agentpipe-scan

Find CI agents that eat untrusted GitHub events and hold secrets

@snyk/axi

Snyk security scans for SAST, SCA and Secrets, with an AI agent-optimized interface

bugx-agent

Host-neutral adversarial white-box and black-box auditing agent

Security Review

Laravel/PHP AI agent skill — compatible with Claude Code, Cursor, Windsurf

ai-appsec

Audit AI applications and agents for security risks before commit, PR, merge, or deployment. Deterministic findings with coverage and evidence receipts.

@openai/codex-security

TypeScript SDK and CLI for Codex Security

agentgov-scanner

Discover AI agents, map their capabilities, and flag security risk. Read-only static analysis.

agenticvulhunter

AgenticVulHunter secure code review tool

agentscan-py

Read-only scanner for exposed AI/agent services: detects unauthenticated endpoints on standard ports and enumerates their API surface.

yandex-yc-tender-llm-service

A package to prevent Dependency Confusion attacks against Yandex.

@scovant/core

Passive AI-agent-readiness scanner (thin launcher for the Python package scovant-core)

@clear-capabilities/agentic-security-scanner

Scanner engine for the agentic-security Claude Code plugin: SAST, SCA with reachability and CISA KEV, secrets, IaC, Haskell and Nix/NixOS, prompt-injection, MCP/agent-tool audit, authZ analysis, SBOM, compliance attestation, and more.

agent-cve-scanners

Offline scanners for the code patterns behind 68 CVEs in 9 AI-agent frameworks, plus MCP tool pinning. No dependencies, no telemetry.

auditagent-toolkit

Toolkit modular de auditoría técnica en Python (solo stdlib)

langchain-tanod

LangChain tools for Tanod: address risk checks, smart-contract scans, MCP/skill package scans, web/DNS/chain reads for AI agents. Pay per call with x402 (USDC on Base); free daily tier, no signup.

leakhunterx-agent

LeakHunterX Security Scanning Agent

litellm-check

Self-audit CLI: scan a codebase and local Python environments for exposure to the compromised LiteLLM v1.107.0 release (PyPI, Docker Hub, GHCR) and generate an evidence report, based solely on LiteLLM's official incident announcement.

llm-security-scanner-skill

Cross-platform AI agent skill for llm-security-scanner - OWASP Top 10 for LLMs scanning from Claude, Gemini, Codex and MCP

pydantic-ai-trustabl

Scan an agent repository for reliability and safety weaknesses from a Pydantic AI agent.

repo-agent-surface-pre-open-audit

Pre-open repo agent-surface audit: per-harness OPEN / OPEN-QUARANTINED / DO-NOT-OPEN verdict on a received repo's complete agent-control surface, before your agent's first git call.

llm-model-security-scanner

Comprehensive enterprise security scanner & proof verification engine for open-source LLMs and Hugging Face repositories

nexus-gateway-sdk

TypeScript SDK for Nexus Gateway — M2M Legal-Code Services for Web3 + Web2 Dependency Fitness Attestation (GHSA/CVE, SPDX license, CycloneDX SBOM, EIP-712 signed attestations, Merkle-anchored public proofs). Native tool wrappers for LangChain.js and Verce

Shieldz MCP

Open-source MCP server for checksum and provenance checks in AI-agent workflows. Homepage: https://shieldz.cash/unlock/ezE1i9Nbn0QdS1xSh0El

Agent Ridge

Agent Ridge finds the security flaws in your online store before attackers do. AI-driven security audits for e-commerce sites and web platforms, with visual evidence and PDF reports.

@agentic-readiness/cli

Command line and local MCP server of the Agentic Readiness Scanner, self-contained: npx @agentic-readiness/cli scan <url>.

@agentic-readiness/core

The Agentic Readiness Scanner engine: fetcher, target resolver, parsers, checks, runner, scoring and reporters, with the catalog and visual system bundled in.

More in Security & AI safety