Security & AI safety

Pentesting & offensive security

763 agents · most starred first

Pentesting & offensive security, page 8 of 8

openai-hacker

hacker of openai python client

pen-tester-agent

A penetration testing agent powered by local LLMs via Ollama

pentestgpt

PentestGPT, a GPT-empowered penetration testing tool

pentesting-claude-skill

AI-powered penetration testing automation using Claude

phantom-agent

Autonomous Offensive Security Intelligence - AI-powered penetration testing

plutonus-llmfuzz

llmfuzz CLI

probegpt

Automated red-team discovery for AI models

ragaai-redteaming

RAGA AI RedTeaming

redteam-os-agent

Pull-based RedOS worker runtime agent for WORKER_RUNTIME task execution.

secagent
sploitx-agents

Reserved for the SploitX project (Agents).

spy-agent

Spy-Agent: Advanced JS Miner

strix-agent

Open-source AI Hackers for your apps

subgpt

Find subdomains with GPT, for free

swarmhawk

Autonomous AI-powered external attack surface assessment

zyron-agentshield

Professional DAST & Pentest Framework

agent-guardian

Open-source red teaming toolkit for AI agents, RAG systems, MCP servers, and tool-using LLM applications.

agenthive-sim

Multi-agent attack simulation framework for AI systems

@integsec/agentic-pentest-proxy

IntegSec Agentic Pentest MCP Proxy — enforce penetration testing engagement scope for AI agents

ultimatrix

AI-powered security team-in-a-box. Multi-agent security testing platform with AutoGen-style orchestration.

agent-strike

Agent Strike — Offensive LLM Security Testing. Coming soon by Sandeep.

pentesty-agent

Pentesty security monitoring agent

llmasm-ananya

LLM Attack Surface Mapper for AI Security Testing

@metaharness/redblue

AI red-teaming for agents and LLM apps you own: adversarial tests for prompt injection, tool misuse, data leakage and jailbreaks, auto-patch, retest, and a report. No shell, no live targets.

finagent-redrange

A reproducible, defensive red-team range for financial-services AI agents.

muhgpt

Human-in-the-loop pentest & OSINT CLI assistant

@anvilwing/vigil

Vigil — an offensive-cyber terminal agent for Computer Network Attack. Exploitation, payload delivery, persistence, lateral movement, credential harvesting, command and control — on authorized target infrastructure.

oh-my-open-pentest

Autonomous Pentest Platform - AI-Driven Security Testing with Multi-Agent Orchestration, Scope Enforcement, and Automated Finding Reports

omega-security-scanner

OMEGA MASTER v10.0 — Ultimate Autonomous Pentest Engine by @c4ccz. 8 Collaborative AI Agents, 5000+ Paths, 3000+ Payloads, Deep Correlation, Attack Chains, Browser Automation.

aether-cyberagent

Elite AI security engineer and autonomous developer agent.

agent-redteam

AI Agent 红队安全测试平台 — 从 CLI 到 Dashboard

agentcyberrange

Async Python SDK for Agent Cyber Range

agentic-redteam

Frontier-Grade AI Agent Red-Teaming & Security Benchmark Harness

superred-claim-agentdojo

AgentDojo SecurityClaim for superred: original injection-task port + bespoke system-purpose-violation goals against the composite AgentDojoTarget

superred-claim-agentharm

AgentHarm SecurityClaim for superred: faithful port of the harmful test_public split (176 behaviors) against the general inspect-agent target, reusing upstream inspect_evals.agentharm tools/grading/judges. 8 per-category subclaims + total.

superred-optimizer-gptfuzzer

GPTFuzzer jailbreak optimizer for superred

superred-target-agentdojo

AgentDojo composite target for superred: union of all four AgentDojo suites with on-demand event-based injection and tool-catalog controllable surface. Tracks the latest released benchmark version (v1.2.2) via agentdojo_target.BENCHMARK_VERSION.

superred-target-dtap-claudecode

Claude Code (claude_agent_sdk) DTAP agent target for superred: subclasses dtap_scaffold.DtapAgentTarget and runs the Claude Agent SDK in an isolated Docker container against the DTAP env MCP proxy, normalizing the in-container transcript into the shared TrajectoryArtifact.

superred-target-inspect-agent

General inspect-ai tool-calling agent target for superred: runs an agent over caller-supplied tools/prompts/model and exposes the message trace. Benchmark-agnostic; reusable by any inspect-tool agentic SecurityClaim.

superred-target-minimal-llm-chat

Minimal single-turn LLM chat target for the superred red-teaming framework

vulgpt

Evidence-first AI-assisted security testing for explicitly authorized web targets.

cot-redteam-agent

Automated Chain-of-Thought Red Teaming Agent

goods-dragon

Advanced Pentesting & Bug Bounty Framework

heretic-agent

Autonomous AI agent that finds business-logic vulnerabilities (BOLA/IDOR, price tampering, workflow bypass, data exposure) — Oracle-verified, ~0 false positives

llm-scanner

Black-box security scanner for LLM chatbots — OWASP LLM Top 10 red-teaming CLI

icoa-cli

ICOA CLI — AI-native competition runtime of the International Cyber Olympiad in AI: learn, practise, and compete in AI & cybersecurity from the terminal (AI4CTF · CTF4AI · CTF4EAI)

@keygraph/shannon

Shannon is an autonomous white-box AI pentester for web applications and APIs, by Keygraph.

swarmattacker

Multi-methodology swarm penetration testing agent built with LangGraph

zen-agent

Open-source offensive security agents for autonomous pentesting

ctf-agent

Autonomous Security Intelligence & Competitive Exploitation Framework

acurist

The ultimate penetration testing agent

agentic-bug-hunter

AI-powered bug bounty hunting — recon to report, in your terminal.

agentred

An open-source red-teaming framework for security assessment of AI agents.

dragonrepo

Automated penetration testing report generator with command tracking and evidence.

guile-agent

Open-source AI Hackers for your apps

hackagent-webui

Prebuilt HackAgent dashboard served by the hackagent CLI.

langchain-darkmoon

LangChain tools for Darkmoon, the local privacy-first autonomous AI penetration testing engine.

nvidia-agent-hardener

A swarm of agents for security purposes: attackers and defenders play 'war games' in order to better protect the victim agent

splitagent

Autonomous dual-team (Purple Team) security framework powered by configurable LLM APIs.

agentsec-agentdrill

Continuous adversarial-testing (proof) engine for AI-agent defenses — run curated attack packs against the deployed stack, verify enforcement with the kill-chain, and publish an honest, reproducible defense benchmark.

redagent

AI Agent Security & Automated Red Teaming Platform

aig-agent-scan

AI Agent Security Scanning Tool - a dynamic black-box security testing tool for running AI Agent platforms

lamia-agent

Open-source AI Hackers for your apps

More in Security & AI safety