Security & AI safety

AI guardrails & agent security

AI guardrails and agent security projects defend AI systems from misuse and attack, covering prompt injection defense, LLM firewalls, permissioning, and secrets scanning. SkillSpector scans agent skills for malicious patterns and data exfiltration, while Infisical secures the secrets and credentials agents depend on.

3,625 agents · most starred first

Top 100 of 3,625

iFixAi★ 46,315

Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.

Anthropic-Cybersecurity-Skills★ 36,445

817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 29 security domains · Apache 2.0

infisical★ 30,631

Infisical is the open-source platform for securing secrets, certificates, access, and AI Agents.

SkillSpector★ 27,009

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.

casdoor★ 14,914

An open-source Agent-first Identity and Access Management (IAM) /LLM MCP & agent gateway and auth server with web UI supporting OpenClaw, MCP, OAuth, OIDC, SAML, CAS, LDAP, SCIM, WebAuthn, TOTP, MFA, Face ID, Google Workspace, Azure AD

opa★ 12,501

Open Policy Agent (OPA) is an open source, general-purpose policy engine.

guardrails★ 7,628

Adding guardrails to large language models.

AI-Infra-Guard★ 7,596

A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

Guardrails★ 7,536

NeMo Guardrails is an open-source library for applying programmable safety and security controls to LLM and agentic applications.

superagent★ 6,883

Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.

agent-governance-toolkit★ 6,584

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

destructive_command_guard★ 6,369

A fast Rust safety hook that blocks destructive shell, git, and filesystem commands before AI coding agents run them. 50+ security packs (databases, Kubernetes, Docker, cloud, Terraform), heredoc/inline-script scanning, CI scan mode, and explain mode; works with Claude Code, Codex, Gemini, Copilot, Cursor, and more.

bla★ 6,280

🛡️ BLA (bla-agents / Blind LLM Agents) — Open-source Blue Defense MCP server & CLI protecting JS/TS, Electron ASAR, WASM, Python, Native Binaries, SQLite, GGUF/Safetensors & Android DEX against AI reverse-engineering agents (REA).

opal★ 5,524

Policy and data administration, distribution, and real-time updates on top of Policy Agents (OPA, Cedar, ...)

nono★ 5,052

agent runtime security - zero trust, zero setup, zero latency agent sandboxing

varlock★ 4,984

AI-safe .env files: Schemas for agents, Secrets for humans.

cerbos★ 4,664

Cerbos is an open-core authorization management platform for authorizing every identity and governing every action across applications, gateways, workloads, and AI agents.

ai.robots.txt★ 4,264

A list of AI agents and robots to block.

agent-scan★ 3,263

Security scanner for AI agents, MCP servers and agent skills.

deepteam★ 3,112

DeepTeam is a framework to red team LLMs and AI agents.

yubikey-agent★ 2,905

yubikey-agent is a seamless ssh-agent for YubiKeys.

openclaw-security-practice-guide★ 2,855

This guide is designed for OpenClaw itself (Agent-facing), not as a traditional human-only hardening checklist.

tirith★ 2,785

Terminal security for developers and AI agents. Intercepts homograph URLs, pipe-to-shell, ANSI injection, obfuscated payloads, data exfiltration, and malicious AI skills/configs before they execute.

skill-scanner★ 2,750

Security Scanner for Agent Skills

OrgKernel★ 2,671

Open-source trust layer for AI agents — cryptographic agent identity (Ed25519), instance-scoped execution tokens, SHA-256 hash-chained audit logging, and enterprise SSO/SCIM federation. The security foundation powering every agent in the Metaprise AURA platform.

Internal-Safety-Collapse★ 2,625

[NeurIPS 2026] Safety failures in coding agents and frontier LLMs. Reproducible workspaces for studying when AI agents generate unsafe data during task completion.

OmniAgent★ 2,547

An agent capable of self-evolving and dynamically hardening security

agent-vault★ 2,518

A HTTP credential proxy and vault for AI agents like Claude Code, OpenClaw, Hermes, custom agents + harnesses, and more.

ADR★ 2,142

ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

cc-safety-net★ 2,079

A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Devin CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.

agentic_security★ 2,047

Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪

aif★ 1,963

On device Firewall for Coding and Personal Agents

awesome-ai-security-tools★ 1,764

A curated list of public-source, research, and commercial tools for AI security and AI-assisted cybersecurity — autotriage, agent security, AI/ML supply chain, pentest agents, AI SAST, LLM-driven fuzzing, threat intelligence, SOC/SIEM triage, reverse engineering, LLM red-teaming, and more.

OpenAPPA★ 1,645

Deterministic guardrails that don't break agents

akto★ 1,550

Akto is the fastest growing AI Security platform for your teams to secure AI agents, MCPs, LLMs, Agent skills, Gen AI apps in your organization.

agentshield★ 1,428

AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️

inspect_petri★ 1,390

An alignment auditing agent capable of quickly exploring alignment hypothesis

reverify★ 1,347

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

bernstein★ 1,216

Open-source AI agent governance. Write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run

numbat★ 1,174

Visibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction.

hol-guard★ 1,115

Open-source antivirus and firewall for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

agentic-radar★ 1,072

A security scanner for your LLM agentic workflows

agentdojo★ 1,061

A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.

rogue★ 1,058

AI Agent Evaluator & Red Team Platform

betterleaks★ 1,023

Scan the world (for secrets)

pipelock★ 1,010

Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.

gpt_jailbreak_status★ 931

This is a repository that aims to provide updates on the status of jailbreaking the OpenAI GPT language model.

api-relay-audit★ 924

Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks. Website: https://apirelayaudit.com

shellfirm★ 920

Safety guardrails for ai coding agents and human terminal commands

awesome-opa★ 905

A curated list of OPA related tools, frameworks and articles

pipelock★ 904

Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.

CrabTrap★ 801

An LLM-as-a-judge HTTP proxy to secure agents in production

codegate★ 790

CodeGate: Security, Workspaces and Multiplexing for AI Agentic Frameworks

ISC-Bench★ 773

Internal Safety Collapse: Turning the LLM or an AI Agent into a sensitive data generator.

Tracekit★ 722

Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.

safelabs-eval★ 713

Red-teaming and evaluation framework for AI agents, built around an OWASP-inspired ASI01–ASI10 taxonomy

AgentDoG★ 710

A Diagnostic Guardrail Framework for AI Agent Safety and Security

arcjet-js★ 700

Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your JS/TS code.

defenseclaw★ 681

Security Governance for Agentic AI

agent-security★ 674

Local-first, open-source security gateway for AI coding agents. Enforce tool-call policies, detect secrets, and audit actions on-device.

JailbreakHub★ 663

A Hub/research area, for jailbreaking LLM's, and breaking their safety filters.

agent-safe-pipeline★ 662

Open-source gateway that puts authorization in front of every action your AI agents, workflows and pipelines take, before it commits: payments, trades, price changes, deployments and API calls run once on a single-use grant, wait for a person, or are refused, as Decionis decides, with chained evidence. Homebrew, Linux, Docker, Helm.

attestix★ 623

AI agent identity, signed credentials, delegated authority and portable governance evidence. Python core and offline verifier SDKs.

thunderid★ 617

ThunderID, an LF Decentralized Trust project, is a high-performance, open-source identity stack designed for developers to secure and manage access for humans, AI agents, and machines through fully composable identity flows.

Adrian★ 596

Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real time, before the agent acts.

prismor★ 581

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)

slowmist-agent-security★ 561

SlowMist Agent Security Skill: A comprehensive security review framework for AI agents operating in adversarial environments. Core principle: Every external input is untrusted until verified.

damn-vulnerable-llm-agent★ 554
emilia-protocol★ 525

Authority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected executor boundaries; the open protocol keeps evidence verifiable.

Aegis★ 524

Runtime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes.

cordum★ 507

The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.

jai★ 500

Jail your AI agent

vArmor★ 497

vArmor is a cloud-native container hardening system that leverages AppArmor/BPF/Seccomp and NetworkProxy technologies to enforce access control from system calls to application protocols — protecting workloads including AI Agents.

nah★ 494

a guard that blocks catastrophic agent actions

statewright★ 493

State machine guardrails for AI agents

awesome-MLSecOps★ 493

A curated list of MLSecOps tools and resources for securing machine learning and AI systems - adversarial ML defense, LLM security, AI red teaming, model scanning, supply-chain protection, and MLOps pipeline security.

agentguard★ 489

Security guard for AI agents — blocks malicious skills, prevents data leaks, protects secrets. 24 detection rules, runtime action evaluation, trust registry.

asqav-sdk★ 489

Python and TypeScript SDKs for verifiable evidence of AI agent actions. Signed receipts, policy enforcement, audit trails. Works with LangChain, CrewAI, MCP.

invariant★ 476

Guardrails for secure and robust agent development

audit-harness★ 468

Three-layer audit enforcement framework for AI agents — hooks, skills, context recovery, and audit-driven daily reports

guardian-agent★ 461

[beta] Guardian Agent: secure ssh-agent forwarding for Mosh and SSH

Sponsio★ 456

Deterministic safety solutions for probabilistic AI agents

ai-jailbreaks★ 451

AI jailbreaks: 35 paste-ready AI jailbreak prompts for 25+ frontier and open-weight models - system prompts, AGENTS.md specs, and Ollama Modelfiles. Built for AI security research and red-team testing.

vault-ssh-helper★ 447

Vault SSH Agent is used to enable one time keys and passwords

crust★ 440

🌟 Open Source AI Agent Security Infrastructure — intercepts and blocks dangerous agent behaviors before they happen. Just one command! Join us to build safer Human-AI Symbiosis!

agent-vault★ 439

Keep your secrets hidden from AI agents.

agent-threat-rules★ 439

Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable, testable rules for prompt injection, tool poisoning, context exfiltration and MCP attacks. Merged into open-source projects at Microsoft, Cisco, Gen Digital, MISP and FINOS. MIT-licensed.

www-project-agentic-skills-top-10★ 437

OWASP Foundation web repository

rules★ 428

Project CodeGuard is an AI model-agnostic security framework and ruleset that embeds secure-by-default practices into AI coding workflows (generation and review). It ships core security rules, translators for popular coding agents, and validators to test rule compliance.

aifw★ 424

AI Agent Identity and Access Management and Inference Firewall

awesome-cybersecurity-agentic-ai★ 422
agentsh★ 411

Execution-Layer Security (ELS) for AI agents — policy-enforced shell with audit.

Agent-Wiz★ 398

A CLI tool for threat modeling and visualizing AI agents built using popular frameworks like LangGraph, AutoGen, CrewAI, and more.

reins★ 394

Stop AI agents from doing things you didn't ask for.

agent-skills-guard★ 392

一款提供Agent Skills安全扫描和可视化管理的桌面应用 | A desktop application that provides security scanning and visual management for Agent Skills.

cursor-security-rules★ 384

This repository contains Cursor Security Rules designed to improve the security of both development workflows and AI agent usage within the Cursor environment. These rules aim to enforce safe coding practices, control sensitive operations, and reduce risk in AI-assisted development.

agentseal★ 384

Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resistance, and audit live MCP servers for tool poisoning.

project-codeguard★ 375

Project CodeGuard is an open-source, model-agnostic security framework that embeds secure-by-default practices into AI coding agent workflows. It provides comprehensive security rules that guide AI assistants to generate more secure code automatically.

openguardrails★ 372

AI agent guardrails for every builder. Local rules, a sandbox and a firewall for your agents, open source.

saf-mcp★ 368

SAF-MCP is a comprehensive security framework for documenting and mitigating threats in the AI Agent ecosystem.

More in Security & AI safety