Awesome AI-Assisted Penetration Testing

February 20, 2026 · View on GitHub

A curated list of open-source AI-assisted penetration testing tools, frameworks, CTF agents, and benchmarks.

Compiled from a systematic review of the field, anchored by the analysis in "What Makes a Good LLM Agent for Real-world Penetration Testing?" (Deng et al., 2025 — arXiv:2602.17622), which surveyed 28 LLM-based pentesting systems and identified two failure categories: Type A (capability gaps) and Type B (complexity barriers).


Contents


Pentesting Agents & Frameworks

Evaluated in the Paper

These systems were directly analysed or benchmarked in Deng et al. (2025). The paper evaluated five of them (marked with results) across XBOW, PentestGPT-Benchmark, and GOAD.

ToolArchitectureYearPaper Results (GPT-5)Links
PentestGPTHuman-in-the-loop copilot, task tree planning2024XBOW 42%, 7/13 machines, 1/5 hostsGitHub · Paper
AutoPTSingle-agent, pentesting state machine2024XBOW 40%, 7/13 machines, 1/5 hostsPaper
PentestAgentMulti-agent with RAG, phase-based planning2024XBOW 49%, 7/13 machines, 1/5 hostsPaper
VulnBotMulti-agent, tri-phase planning2025XBOW 45%, 8/13 machines, 1/5 hostsPaper
CochiseMulti-agent, AD-specialised, hierarchical2025XBOW 43%, 4/13 machines, 2/5 hostsPaper
PENTESTGPT V2Tool Layer + TDA-EGATS + Memory2025XBOW 85%, 12/13 machines, 4/5 hostsPaper · Code
RapidPenSingle-agent, ReAct with RAG2025Surveyed (not benchmarked)Paper
xOffenseMulti-agent, fine-tuned knowledge2024Surveyed (not benchmarked)Paper
TermiAgentMulti-agent, memory tree2024Surveyed (not benchmarked)Paper
HackSynthSingle-agent, evaluation framework2024Surveyed (not benchmarked)Paper
MAPTAMulti-agent, web pentesting2025Surveyed (not benchmarked)Paper

Additional Agents

Open-source tools and frameworks discovered beyond the paper's survey.

ToolDescriptionLinks
CAICybersecurity AI framework by Alias Robotics. REPL-based pentesting with Phoenix/OTel tracing, JSONL recording, and CAIBench evaluation.GitHub
MANTISMulti-agent pentesting framework on smolagents. Structured state store, HITL operator shell, typed security tool wrappers, OpenTelemetry tracing.GitHub
ShannonAutonomous AI hacker achieving 96.15% on XBOW (hint-free, source-aware). Hunts for attack vectors in code and uses a built-in browser to execute real exploits.GitHub
PentAGIFully autonomous AI agent system with 20+ built-in security tools. Supports OpenAI, Anthropic, Ollama, AWS Bedrock, Google AI, DeepSeek.GitHub
hackingBuddyGPTFramework for LLM-driven security testing. Includes "Wintermute" for Linux privilege escalation via SSH. GitHub Accelerator 2024, presented at FSE'23.GitHub
StrixGraph-based parallel agent workflows for pentesting. Assigns specialised agents to different targets, includes HTTP proxy, browser automation, and terminal environments.GitHub
NeuroSploitAI pentesting framework (v3) with 100 vulnerability types across 10 categories. 3-stream parallel pentesting, isolated Kali Docker containers, anti-hallucination pipeline.GitHub
RedamonAI-powered red team framework automating recon to post-exploitation. Neo4j graph database as single source of truth, LangGraph-based autonomous agent, MCP tool selection.GitHub
HexStrike AIMCP server enabling AI agents (Claude, GPT, etc.) to run 150+ cybersecurity tools autonomously. Bridges LLMs with real-world offensive security capabilities.GitHub
Pentest CopilotBrowser-based AI hacking assistant with integrated Kali Linux container, VPN integration, chain-of-thought reasoning, and RAG.GitHub
ReaperGo-based application security testing framework by Ghost Security. MITM HTTPS proxy for AI agents with autonomous attack type selection. Apache-2.0.GitHub
AutoPentesterLLM agent framework with RAG, repetition identifier (90.5% loop reduction), and results verifier. 27% better subtask completion than PentestGPT.GitHub · Paper
AutoPentestCLI tool for autonomous black-box penetration tests using GPT-4o and LangChain. Automated feedback loop with optional human review.GitHub · Paper
NebulaAI-powered pentesting assistant for recon, note-taking, and vulnerability analysis. Integrates Llama-3.1, Mistral-7B, DeepSeek-R1, and OpenAI. BSD-2-Clause.GitHub
AI-OPSPentesting AI assistant based on open-source LLMs. Focuses on exploit development, vulnerability research, and code analysis.GitHub
FlokiAgentic workflow framework for cybersecurity built on Dapr. Service-to-service invocation, pub/sub messaging, workflow API, and state management.GitHub
TARSAI-powered pentesting tool that builds agents using existing cybersecurity tools for vulnerability scanning and real-time countermeasure generation.GitHub
DecepticonAutonomous multi-agent red team testing service built on LangChain/LangGraph.GitHub

CTF-Focused Agents

ToolDescriptionLinks
D-CIPHERMulti-agent CTF framework (Planner + Executors + Auto-prompter). SOTA: 22.0% NYU CTF Bench, 22.5% Cybench, 44.0% HackTheBox.GitHub · Paper
CTFAgentPlan-and-execute agent with stateful task tree, two-stage RAG, and environmental augmentation. Surpasses ~94% of CTF teams in HITL mode. Top 23.6% in picoCTF2024.Paper (ScienceDirect)
Cyber-ZeroAmazon Science. Trains cybersecurity agents from CTF writeups without runtime environments. Cyber-Zero-32B matches DeepSeek-V3 and Claude 3.5 Sonnet.GitHub · Paper
InterCode-CTF AgentDemonstrates 95% on InterCode-CTF using ReAct&Plan prompting with expanded toolsets. Saturated this benchmark, pushing the field to harder evaluations.GitHub · Paper
llm-ctf-agentBoilerplate for developing and evaluating LLM-based CTF agents. Framework for running agents against challenges, managing LLM interactions, and logging.GitHub

Benchmarks & Evaluation

BenchmarkDescriptionLinks
XBOW104 web security CTF tasks (SQLi, XSS, auth bypass). Used to evaluate Type A failures. Commercial platform.Website
PentestGPT Benchmark13 HTB/VulnHub machines (Easy to Hard), 9-22 subtasks each. End-to-end pentesting evaluation.Paper
GOAD5-host multi-domain Active Directory lab. Requires credential chaining, Kerberoasting, lateral movement. Tests Type B failures.GitHub
AutoPenBenchDocker-based containerised vulnerable environments with milestone-based metrics. Synthetic + real-world CTF-style tasks.GitHub · Paper
Cybench40 professional-level CTF tasks from 4 competitions across 6 domains. Used by US AISI and UK AISI for pre-deployment model testing.GitHub · Paper
NYU CTF Bench200 dockerised CSAW CTF challenges across 6 categories (web, pwn, forensics, rev, crypto, misc).GitHub · Paper
CAIBenchMeta-benchmark integrating 10,000+ instances across 5 evaluation categories including Jeopardy CTFs, Attack/Defence CTFs, and Cyber Range exercises.Paper
3CB15 original CTF challenges covering all MITRE ATT&CK categories. Novel challenges absent from model training data. Used by UK AISI.Website · Paper
CTFusionStreaming evaluation framework built on live CTFs to prevent data contamination. Implemented as MCP server on CTFd platform.Paper
HackTheBox AI RangeCommercial platform for continuous real-world AI agent evaluation against OWASP Top 10 (2025).Website
AI-Pentest-BenchmarkCommunity benchmark for evaluating pentesting AI.GitHub

ResourceDescriptionLinks
awesome-cybersecurity-agentic-aiCurated list of agentic AI frameworks and cybersecurity tools.GitHub
Awesome-LLM4CybersecurityOverview of LLMs for cybersecurity covering offensive and defensive applications.GitHub
AI-agents-for-cybersecurityCourse materials for AI Agents and RAG for Cybersecurity Operations by Omar Santos.GitHub

Key Concepts from the Paper

The paper provides a framework for understanding why AI pentesting agents succeed or fail, which is useful context for evaluating any tool on this list.

Failure Taxonomy

  • Type A failures (42%) — Capability gaps: missing tools, incorrect syntax, knowledge gaps. Addressed by better tool interfaces, RAG, and engineering.
  • Type B failures (58%) — Complexity barriers: context forgetting (18%), premature commitment (16%), exploration-exploitation imbalance (12%), multi-step chain failures (12%). Require architectural solutions.

Architecture Components (PENTESTGPT V2)

  • Tool & Skill Layer — 38 typed tool interfaces with input schemas, structured output parsing, pre/postconditions. Skill composition for multi-tool attack patterns. +14% on XBOW in ablation.
  • Task Difficulty Assessment (TDA) — Four dimensions: horizon estimation, evidence confidence, context load, historical success rate. Drives exploration vs exploitation decisions.
  • Evidence-Guided Attack Tree Search (EGATS) — UCB node selection with difficulty penalties, TDI-guided mode switching, evidence-based pruning.
  • Memory Subsystem — Structured state store (hosts, services, credentials, sessions, vulnerabilities), selective context injection, branch summaries.

What Remains Hard

  • Creativity barrier — Novel exploitation requiring out-of-distribution reasoning
  • Adversarial environments — Honeypots, canary tokens, deceptive services
  • Temporal scale — Cross-session continuity for multi-week engagements

Contributing

Contributions welcome. Please open a PR or issue to add tools, correct information, or suggest improvements. When adding a tool, include:

  • Name and brief description
  • GitHub link (if open-source)
  • Paper link (if published)
  • Whether it was evaluated on any standard benchmark

License

This list is released under CC0 1.0. The tools listed have their own licenses.