Damn Vulnerable MCP Server - A deliberately vulnerable implementation of the Model Context Protocol (MCP) for educational purposes.
otto-support - A vulnerable MCP server implementation using mcp-go with tiered authentication (4 roles), 19 tools, and built-in sandboxed container with Claude Code for practicing privilege escalation and tool misuse.
vulnerable-mcp-servers-lab - A collection of servers which are deliberately vulnerable to learn Pentesting MCP Servers.
FinBot Agentic AI Capture The Flag (CTF) Application - FinBot is an Agentic Security Capture The Flag (CTF) interactive platform that simulates real-world vulnerabilities in agentic AI systems using a simulated Financial Services-focused application.
AI-Red-Teaming-Playground-Labs - AI Red Teaming playground labs to run AI Red Teaming trainings including infrastructure.
Damn Vulnerable LLM Agent - Intentionally vulnerable LLM agent for learning about prompt injection, tool misuse, and agent security
LLMVault - An open-source CTF-style LLM security lab for learning the OWASP LLM Top 10 through hands-on vulnerable exercises covering prompt injection, RAG attacks, system prompt leakage, tool misuse, and agent security.
AI Security Ops - Weekly podcasts from Black Hills Information Security exploring how AI transforms cybersecurity—covering emerging threats, tools, and trends with practical, actionable knowledge.
ATLAS Knowledge Base Agent - Open-source AI assistant for exploring the ATLAS knowledge base with natural language, MCP server access, and customizable agent workflows.
Adversarial Robustness Toolkit - ART focuses on the threats of Evasion (change the model behavior with input modifications), Poisoning (control a model with training data modifications), Extraction (steal a model through queries) and Inference (attack the privacy of the training data)
cleverhans - An adversarial example library for constructing attacks, building defenses, and benchmarking both
foolbox - A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX
TextAttack - A Python framework for adversarial attacks, data augmentation, and model training in NLP
Counterfit - generic automation layer for assessing the security of machine learning systems
OffsecML Playbook - A collection of offensive and adversarial TTPs with proofs of concept
BadDiffusion - Official repo to reproduce the paper "How to Backdoor Diffusion Models?" published at CVPR 2023
secml-torch - SecML-Torch: A Library for Robustness Evaluation of Deep Learning Models
ai-scanner - Open-source web application for AI model security assessments, built on NVIDIA garak. Features 179 probes, multi-target scanning, scheduled scans, ASR scoring, and SIEM integration.
promptfoo - Test your prompts, agents, and RAGs. Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration.
PyRIT - The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.
PurpleLlama - Set of tools to assess and improve LLM security.
augustus - LLM security testing framework for detecting prompt injection, jailbreaks, and adversarial attacks. 190+ probes, 28 providers, single Go binary. Production-ready with concurrent scanning, rate limiting, and retry logic.
FuzzyAI - A powerful tool for automated LLM fuzzing. It is designed to help developers and security researchers identify and mitigate potential jailbreaks in their LLM APIs.
EasyJailbreak - An easy-to-use Python framework to generate adversarial jailbreak prompts.
gptfuzz - Official repo for GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
llamator - Framework for testing vulnerabilities of large language models (LLM).
agentic_security - Agentic LLM Vulnerability Scanner / AI red teaming kit
Agentic Radar - Open-source CLI security scanner for agentic workflows.
Agentic AI & MCP Attack Tools
RAMPART - pytest-native safety and security testing framework for agentic AI applications.
AI-Infra-Guard - A comprehensive, intelligent, and easy-to-use AI Red Teaming platform developed by Tencent Zhuque Lab. Integrates modules for Infra Scan, MCP Scan, and Jailbreak Evaluation, providing a one-click web UI, REST APIs, and Docker-based deployment for comprehensive AI security evaluation.
AIMap - Internet-scale discovery and security testing platform for exposed AI agent infrastructure. Queries Shodan for MCP servers, Ollama instances, vLLM/LiteLLM proxies, and more — then fingerprints, scores risk, and launches protocol-specific attack suites with real-time streaming results.
AI-Assisted Offensive Security
PentestGPT - A GPT-empowered penetration testing tool
HackingBuddyGPT - Helping Ethical Hackers use LLMs in 50 Lines of Code or less
cai - Cybersecurity AI (CAI), an open Bug Bounty-ready Artificial Intelligence (paper)
shannon - Fully autonomous AI pentester for web apps and APIs by Keygraph. White-box security testing that analyzes source code, identifies attack vectors, and executes real exploits. 96.15% success rate (100/104 exploits) on XBOW benchmark.
strix - Strix are autonomous AI agents that act just like real hackers - they run your code dynamically, find vulnerabilities, and validate them through actual proof-of-concepts
redamon - AI-powered agentic red team framework that automates offensive security operations from reconnaissance to exploitation to post-exploitation with zero human intervention.
CyberStrikeAI - AI-native security testing platform built in Go. Integrates 100+ security tools with an intelligent orchestration engine, role-based testing with predefined security roles, skills system, and comprehensive lifecycle management. Uses MCP protocol and AI agents for end-to-end automation from conversational commands to vulnerability discovery.
HexStrikeAI - HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research.
mcp-for-security - A collection of Model Context Protocol servers for popular security tools like SQLMap, FFUF, NMAP, Masscan and more. Integrate security testing and penetration testing into AI workflows.
mcp-security-hub - A growing collection of MCP servers bringing offensive security tools to AI assistants. Nmap, Ghidra, Nuclei, SQLMap, Hashcat and more.
Steganography & Covert Channels
ST3GG - All-in-one steganography suite with multi-layer encoding, image and audio steganography, and steganalysis tools for detecting hidden data in AI-generated media.
Benchmarks & Evaluations
ISC-Bench - Internal Safety Collapse: jailbreaks any frontier LLM (Claude Opus 4.6, GPT-5.4) in pass@3 via normal task completion — no adversarial prompting. Black-box, cross-domain, cross-science. Novel failure mode.[Paper]
jailbreakbench - JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]
AgentDojo - A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
AIRTBench - Code Repository for: AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models
AgentDoG - AgentDoG is a risk-aware evaluation and guarding framework for autonomous agents. It focuses on trajectory-level risk assessment, aiming to determine whether an agent's execution trajectory contains safety risks under diverse application scenarios.
AICGSecEval - Tencent's comprehensive evaluation benchmark for AI code generation security, covering 10 CWE categories with automated test harness
Inspect - Framework for large language model evaluations by the UK AI Security Institute. 200+ pre-built evaluations covering prompt engineering, tool usage, multi-turn dialog, and model-graded scoring.
sec-code-bench - Alibaba's benchmark for evaluating LLM code security capabilities across 17 vulnerability categories and 4 programming languages
Defense & Security Controls
Input/Output Guardrails
NeMo-Guardrails - NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
LlamaFirewall - LlamaFirewall is a framework designed to detect and mitigate AI centric security risks, supporting multiple layers of inputs and outputs, such as typical LLM chat and more advanced multi-step agentic operations.
llm-guard - LLM Guard by Protect AI is a comprehensive tool designed to fortify the security of Large Language Models (LLMs).
Guardrails.ai - Guardrails is a Python package that lets a user add structure, type and quality guarantees to the outputs of large language models (LLMs)
TrustGate - Generative Application Firewall (GAF) to detect, prevent and block attacks against GenAI Applications
ZenGuard AI - The fastest Trust Layer for AI Agents
LocalMod - Self-hosted content moderation API with prompt injection detection, toxicity filtering, PII detection, and NSFW classification. Runs 100% offline.
DynaGuard - A Dynamic Guardrail Model With User-Defined Policies
AprielGuard - 8B parameter safety–security safeguard model
Safe Zone - Safe Zone is an open-source PII detection and guardrails engine that prevents sensitive data from leaking to LLMs and third-party APIs.
superagent - Superagent provides purpose-trained guardrails that make AI-agents secure and compliant.
ShellWard - AI Agent Security Middleware with 8-layer defense against prompt injection, data exfiltration & dangerous commands. Zero dependencies.
-
Agent Runtime Security & Sandboxing
OpenShell - OpenShell is the safe, private runtime for autonomous AI agents. It provides sandboxed execution environments governed by declarative YAML policies that prevent unauthorized file access, data exfiltration, and uncontrolled network activity.
OpenSandbox - Secure, Fast, and Extensible Sandbox runtime for AI agents. Multi-language SDKs, Docker/Kubernetes runtimes, gVisor/Kata Containers/Firecracker isolation. CNCF Landscape project.
CubeSandbox - Instant, concurrent, secure & lightweight sandbox for AI agents by Tencent Cloud. Sub-60ms cold start, <5MB memory overhead, E2B SDK compatible. Built on RustVMM and KVM with extreme isolation (dedicated kernel + eBPF).
Aegis - Open-source EDR for AI agents by Antropos. Monitor processes, files, network, and behavior of autonomous AI agents in real time. No telemetry, no cloud, everything stays local.
Microsoft Agent Governance Toolkit - AI Agent Governance Toolkit from Microsoft — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
agentfield - Open-source control plane for agent systems with cryptographic identity, policy enforcement, and audit-friendly observability.
leash - Leash wraps AI coding agents in containers and monitors their activity.
vibekit - Run Claude Code, Gemini, Codex — or any coding agent — in a clean, isolated sandbox with sensitive data redaction and observability baked in.
pipelock - Security harness for AI agents — egress proxy with DLP scanning, SSRF protection, MCP response scanning, and workspace integrity monitoring
skill-scanner - A security scanner for AI Agent Skills that detects prompt injection, data exfiltration, and malicious code patterns. Combines pattern-based detection (YAML + YARA), LLM-as-a-judge, and behavioral dataflow analysis for comprehensive threat detection.
MCP Security
MCP-Security-Checklist - A comprehensive security checklist for MCP-based AI tools. Built by SlowMist to safeguard LLM plugin ecosystems.
Awesome-MCP-Security - Everything you need to know about Model Context Protocol (MCP) security.
secure-mcp-gateway - This Secure MCP Gateway is built with authentication, automatic tool discovery, caching, and guardrail enforcement.
mcp-context-protector - context-protector is a security wrapper for MCP servers that addresses risks associated with running untrusted MCP servers, including line jumping, unexpected server configuration changes, and other prompt injection attacks
mcp-guardian - MCP Guardian manages your LLM assistant's access to MCP servers, handing you realtime control of your LLM's activity.
MCP Audit VSCode Extension - Audit and log all GitHub Copilot MCP tool calls in VSCode centrally with ease.
MCP-Scan - A security scanning tool for MCP servers
ATR (Agent Threat Rules) - Open-source detection rules for AI agent threats. 108 regex rules covering prompt injection, tool poisoning, credential exfiltration across 9 categories. Used by Cisco AI Defense. MIT licensed.
MCPProxy - Local-first MCP proxy with per-tool SHA-256 quarantine to detect tool-poisoning and rug-pull attacks, automatic sensitive-data and secret scanning of tool calls, Docker sandbox isolation for untrusted MCP servers, and OAuth 2.1. MIT licensed.
Model & Artifact Scanning
modelscan - ModelScan is an open source project from Protect AI that scans models to determine if they contain unsafe code.
fickling - A Python pickling decompiler and static analyzer
medusa - AI-first security scanner with 74+ analyzers, 180+ AI agent security rules, intelligent false positive reduction. Supports all languages. CVE detection for React2Shell, mcp-remote RCE.
julius - LLM service fingerprinting tool for security professionals. Detects 32+ AI services (Ollama, vLLM, LiteLLM, Hugging Face TGI, etc.) during penetration tests and attack surface discovery. Uses HTTP-based service fingerprinting to identify server infrastructure.
a2a-scanner - Scan A2A agents for potential threats and security issues
AI-Assisted Defensive Security
Claude Code Security Review - An AI-powered security review GitHub Action using Claude to analyze code changes for security vulnerabilities.
deepsec - Agent-powered vulnerability scanner by Vercel Labs for finding hard-to-spot issues in large codebases using coding agents. Supports parallel scanning, PR diff review, and CI/CD integration.
defending-code-reference-harness - Reference implementation for autonomous vulnerability discovery and remediation using Claude. Includes threat modeling, scanning, triage, and patching skills.
Visa Vulnerability Agentic Harness - Agentic SAST pipeline with 11 stages from detection through LLM-powered remediation and adversarial validation. Outputs SARIF, integrates with Claude Code, Copilot, and Gemini.
GhidraGPT - Integrates GPT models into Ghidra for automated code analysis, variable renaming, vulnerability detection, and explanation generation.
IDAssist - AI-Powered Reverse Engineering Plugin for IDA Pro. Integrates LLM-powered analysis into IDA's interface with semantic knowledge graphs, RAG document search, and support for multiple LLM providers (OpenAI, Anthropic, Ollama, LiteLLM). Analyzes functions, suggests renames, answers questions about code.
ThreatForest - Agentic threat modeling platform built on Strands framework. Autonomously generates attack trees from repositories, maps attack steps to MITRE ATT&CK techniques, and produces actionable mitigation recommendations.
claude-grc-plugin - Claude Code plugin that turns Claude into a senior GRC analyst. 72+ reference files covering 15 frameworks (NIST 800-53, FedRAMP, ISO 27001, SOC 2, etc.), 24 slash commands, and deep domain knowledge for federal and commercial compliance work.
Vigil SOC - A comprehensive open-source security operations platform for AI agents, enabling real-time monitoring, threat detection, and incident response for AI-powered environments.
Trusera ai-bom - AI Bill of Materials — discover every AI agent, model, and API in your infrastructure
Agentic AI Security Skills
Elastic Agent Skills - Collection of skills for Elastic's AI assistant, enabling natural language security investigations across logs, traces, and threat intelligence
Ghost Security Skills - Agent application security (appsec) skills and tools for Claude Code
tm_skills - Agent skills to help with Continuous Threat Modeling
Trail of Bits Skills Marketplace - Trail of Bits Claude Code skills for security research, vulnerability detection, and audit workflows
Semgrep Skills - Official Semgrep skills for Claude Code and other AI coding assistants. Provides security scanning, code analysis, and vulnerability detection capabilities directly in your AI-assisted development workflow.
claude-bug-bounty - Claude Code skill for AI-assisted bug bounty hunting. Automates reconnaissance, IDOR, XSS, SSRF, OAuth, GraphQL, and LLM injection testing with 4-gate validation checklist and report generation.
Anthropic Cybersecurity Skills - 734+ structured cybersecurity skills for AI agents. MITRE ATT&CK mapped, agentskills.io standard. Compatible with Claude Code, Copilot, Codex CLI, Cursor, and Gemini CLI.
llm-sast-scanner - SAST skill for AI coding agents (Claude Code, Codex, etc.) with structured vulnerability detection across 34 classes. Features source-to-sink taint analysis, Judge verification for false positive reduction, and 99%+ precision/recall on benchmarks.
sast-skills - Collection of agent skills that turn your AI coder into a SAST scanner
pentest-ai-agents - 31 Claude Code subagents for offensive security. Specialized AI subagents for recon, web, AD, cloud, mobile, wireless, social engineering, payload crafting, reverse engineering, exploit chaining, detection engineering, forensics, and report generation. Tier 2 agents can execute tools directly with approval gates.
-
Security-Focused AI Models
VulnLLM-R-7B - Specialized reasoning LLM for vulnerability detection. Uses Chain-of-Thought reasoning to analyze data flow, control flow, and security context. Outperforms Claude-3.7-Sonnet and CodeQL on vulnerability detection benchmarks. Only 7B parameters making it efficient and fast.
Foundation-Sec-8B-Reasoning - Llama-3.1-FoundationAI-SecurityLLM-8B-Reasoning is an open-weight, 8-billion parameter instruction-tuned language model specialized for cybersecurity applications. It extends the Foundation-Sec-8B base model with instruction-following and reasoning capabilities.
Antares (1B & 350M) - Agentic models for vulnerability localization by fdtn-ai. Available in 2B and 0.4B parameter variants, designed to autonomously identify and localize vulnerabilities in code.
CyberSecQwen-4B - _4B-parameter CTI specialist fine-tuned from Qwen3-4B-Instruct-2507 for cybersecurity threat intelligence.
Meta-SecAlign-8B / Meta-SecAlign-70B - Security-aligned Llama models fine-tuned to resist prompt injection attacks, maintaining instruction hierarchy even under adversarial inputs
Lily-Cybersecurity-7B - Cybersecurity-tuned 7B chat model optimized for security analysis, vulnerability explanation, and threat intelligence tasks.
Safety Classifiers & Prompt Injection Detection
Llama-Guard-4-12B - Meta's latest multimodal safety classifier for detecting harmful content in LLM inputs and outputs across text and image modalities.
Llama-Prompt-Guard-2-86M - Lightweight 86M parameter model from Meta for detecting prompt injection and jailbreak attempts in production LLM pipelines.
ShieldGemma-2B - Google's 2B parameter text safety classifier for detecting harmful content, built on the Gemma architecture.
DeBERTa Prompt Injection Detector v2 - Protect AI's DeBERTa-v3-base fine-tuned for prompt injection detection, widely used in production LLM guardrail pipelines.
Prompt Injection Sentinel - ModernBERT-large model fine-tuned for prompt injection and jailbreak classification with low false-positive rate.
Nemotron 3.5 Content Safety - NVIDIA's 4B-parameter multimodal content safety model unifying text+image input guardrails, multilingual support (35+ languages), customizable enterprise policy enforcement, and auditable reasoning in a single inference call. Successor to Nemotron 3 Content Safety.
BrowseSafe - Specialized security model for detecting prompt injection attacks in AI browser agents. Achieves 90.4% F1 score on BrowseSafe-Bench, optimized for real-time async classification of raw HTML content.
Domain-Adapted Security Language Models
ATTACK-BERT - Sentence-transformer model for mapping security text to MITRE ATT&CK techniques.
CySecBERT - BERT model adapted for cybersecurity and CTI tasks through domain-specific pre-training.
Datasets
SafetyPrompts - Curated collection of safety-relevant prompts for evaluating LLM safety and security properties.
Do-Not-Answer - Dataset of prompts that responsible LLMs should not answer, for safety evaluation and red teaming.
JailBreakV-28K - Large-scale dataset of 28,000 jailbreak prompts for benchmarking LLM safety.
CL4R1T4S - Leaked system prompts from ChatGPT, Claude, Gemini, Grok, Perplexity, Cursor, Lovable, Replit, and other major AI tools. Largest known collection of production system prompts for transparency and attack-surface research.
LEAKHUB - System Prompt Leak Leaderboard — community platform for tracking and ranking system prompt leaks across AI products.
Leaked System Prompts - Collection of leaked system prompts from commercial AI tools — useful for understanding real-world prompt engineering and attack surfaces.
llm-attacks - Universal and Transferable Attacks on Aligned Language Models
llm-security - New ways of breaking app-integrated LLMs
Plexiglass - A toolkit for detecting and protecting against vulnerabilities in Large Language Models (LLMs).
Prompt Hacking Resources - A list of curated resources for people interested in AI Red Teaming, Jailbreaking, and Prompt Injection
Giskard - Open-Source Evaluation & Testing for AI & LLM systems
blackice - BlackIce is an open-source containerized toolkit designed for red teaming AI models, including Large Language Models (LLMs) and classical machine learning (ML) models. Inspired by the convenience and standardization of Kali Linux in traditional penetration testing, BlackIce simplifies AI security assessments by providing a reproducible container image preconfigured with specialized evaluation tools.
ai-best-practices - Semgrep Pro Rules to ensure code using LLMs is following best practices. 58 rules, 102 sub-rules covering 6 providers + MCP + Claude Code & Cursor hooks + LangChain. Detects hardcoded API keys, prompt injection risks, missing safety checks, and unhandled errors across 7 languages.
G0DM0D3 - Open-source multi-model chat interface for red teaming with 50+ models via OpenRouter. Features GODMODE CLASSIC (5 jailbreak combos), ULTRAPLINIAN multi-model evaluation, Parseltongue input perturbation engine with 33 red team techniques, and AutoTune adaptive sampling for AI safety research.
L1B3RT4S - Collection of jailbreak and liberation prompts for major LLMs. Curated library of adversarial prompts designed to test and evaluate AI safety guardrails across ChatGPT, Claude, Gemini, and other frontier models.
OBLITERATUS - Abliteration toolkit that removes refusal behaviors from open-source LLMs without retraining. Modifies model weights to eliminate safety-aligned refusal responses, enabling unrestricted model behavior research.
T3MP3ST - Autonomous red teaming platform and multi-agent offensive-security meta-harness. Coordinates swarms of AI agents for coordinated adversarial testing of frontier AI systems.
P4RS3LT0NGV3 - Universal text transformation and promptcrafting toolkit. Supports translation, mutation, encoding/decoding, and adversarial prompt engineering for jailbreak payload construction.
claude-secure-coding-rules - Open-source security rules that guide Claude Code to generate secure code by default.
DeepTeam - LLM red teaming framework with 40+ attack methods including prompt injection, jailbreaking, and RAG poisoning. Integrates with CI/CD pipelines.
burpgpt - A Burp Suite extension that integrates OpenAI's GPT to perform an additional passive scan for discovering highly bespoke vulnerabilities and enables running traffic-based analysis of any type.
guardian-cli - AI-Powered Security Testing & Vulnerability Scanner. Guardian CLI is an intelligent security testing tool that leverages AI to automate penetration testing, vulnerability assessment, and security auditing.
Violin - Supervised, agentic Hermes Agent pentest profile: 31 skill-based playbooks (OWASP Top 10, API Top 10, LLM Top 10) with interactive scoping, scope validation, and approval gates for authorised recon, exploit validation, and reporting.
NeuroSploit - Autonomous multi-model pentesting harness in Rust. LLM pool drives recon, agent selection, exploit chaining, and cross-model validation voting across black-box, white-box, grey-box, and cloud engagement modes.
OpenHack - AI-powered multi-agent scanner that autonomously finds SQLi, XSS, IDOR, and auth bypass in your codebase, then verifies each finding through sandbox execution and browser replay. On par with Claude Opus 4.6 at roughly 40x lower cost.
PentAGI - Fully autonomous multi-agent system for complex penetration testing tasks. Sandboxed Docker execution, multi-provider LLM support (OpenAI, Anthropic, Gemini, Ollama, DeepSeek), knowledge graph integration, and real-time agent supervision.
V3SP3R - AI-powered hardware hacking companion for the Flipper Zero. Natural language interface for controlling hardware attacks, with smart glasses integration for hands-free operation.
An open-source, privacy-focused project that acts as a layer of security within a developer's Code Generation AI workflow
Future AGI - Open-source self-hostable platform with built-in real-time guardrails for unsafe outputs (jailbreak, PII, injection, toxicity), evals, tracing, simulations, and gateway for LLM and agent applications.
SkillSpector - Security scanner for AI agent skills. Detects 64 vulnerability patterns across 16 categories with static analysis + optional LLM semantic evaluation. Multi-format output (JSON, Markdown, SARIF).
Project CodeGuard - CoSAI Open Source Project for securing AI-assisted development workflows. CodeGuard provides security controls and guardrails for AI coding assistants to prevent vulnerabilities from being introduced during AI-generated code development.
AgentLens - Agent observability and replay tooling for AI safety & interpretability research. Harness for running multi-session agent trajectories, capturing them in ATIF format, and tracking file state changes across sessions. Built for studying LLM agent behavior across multi-turn, multi-session, multi-agent interactions.
claude-code-devcontainer - Sandboxed devcontainer for running Claude Code in bypass mode safely. Built for security audits and untrusted code review.
claude-code-safety-net - A Claude Code plugin that acts as a safety net, catching destructive git and filesystem commands before they execute
OneCLI - Open-source credential vault for AI agents. Rust HTTP gateway intercepts agent requests and injects API credentials transparently so agents never hold raw keys. AES-256-GCM encryption, per-agent scoping, full audit trail.
OpenSandbox - Secure, Fast, and Extensible Sandbox runtime for AI agents. Multi-language SDKs, Docker/Kubernetes runtimes, gVisor/Kata Containers/Firecracker isolation. CNCF Landscape project.
openclaw-shield - Security plugin for OpenClaw agents - prevents secret leaks, PII exposure, and destructive command execution
clawsec - Security scanner and hardening tool for OpenClaw deployments. Provides security assessments, configuration auditing, and vulnerability detection specifically for OpenClaw gateway and agent configurations.
nanoclaw - Lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK. First AI assistant to support Agent Swarms for collaborative agent teams.
secureclaw - Automated security hardening for OpenClaw AI agents by Adversa AI. 51 audit checks, 12 behavioral rules, 9 scripts, 4 pattern databases. Full OWASP ASI Top 10 coverage. Protects against prompt injection, credential theft, supply chain attacks, and privacy leaks.
defenseclaw - Enterprise governance layer for OpenClaw from Cisco AI Defense. Scans skills, MCP servers, and plugins with built-in CodeGuard SAST, tool call inspection engine, LLM guardrail proxy, and SIEM integration. Auto-blocks HIGH/CRITICAL findings.
microsandbox - Lightweight microVM sandbox for running untrusted AI-generated code safely with strong isolation guarantees
Adrian - Open-source, AARM-aligned runtime security monitoring and control engine for AI agents by Secure Agentics. Analyses agent activity logs (tool calls, actions, outputs) and reasoning traces to detect malicious, misaligned, or out-of-remit behaviour, with optional in-flight intervention (audit vs block mode). Python (LangChain/LangGraph) and TypeScript SDKs, fully self-hostable offline. Apache-2.0.
HOL Guard - Local-first security harness that intercepts tool calls in AI coding agents (Codex, Claude Code, Cursor, Gemini, Copilot, Hermes, OpenCode) before files change or network is contacted. Pre-tool hooks, approval center, supply-chain advisory scanning, and optional Guard Cloud sync.
AiSOC - Open-source, self-hostable AI-powered SOC that ingests security events, correlates them, runs autonomous AI-driven investigations via LangGraph, and surfaces results in a unified console. Features full agent decision audit trail, public eval harness in CI, and 52 first-party connectors. MIT licensed.
Google's decoupled, sequential, security-focused pipeline of agentic AI skills for autonomously reviewing, deduplicating, validating, reproducing, and patching vulnerabilities across codebases of any scale. Features a multi-stage pipeline (architecture analysis → threat modeling → research → review → reproduction → patching → calibration → reflection), built-in sandboxing, and a continuous learning loop that adapts across iterative runs. Supports RTL hardware, IaC, ML pipelines, and compiled binaries.
ottosulin/awesome-ai-security
