Red Team Python Packages

adversarial-robustness-toolbox

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

phantom-agent

Autonomous Offensive Security Intelligence AI-powered multi-agent penetration testing

mockssh

Mock an SSH server and define all commands it supports (Python, Twisted)

adscan

Free Active Directory pentesting tool and Linux CLI for AD enumeration, BloodHound, Kerberoasting, ADCS, DCSync, and attack paths.

nostos

Zero-dependency Python CLI for batch-updating and curating a fleet of git repositories. SQLite metadata index, fail-closed upstream probes (GitHub / GitLab / Gitea), weekly digest, Obsidian bridge.

ptai

The most autonomous pentesting AI on the market. MCP server + Python agents with 150+ security tools, exploit chaining, and PoC validation.

agent-security-harness

466 security tests for AI agent systems — MCP, A2A, x402/L402, decision governance, benchmark integrity, skill supply chain. AIUC-1 pre-cert, NIST AI 800-2 aligned, 5 DOIs. v4.3.0

agentseal

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.

reconninja

⚡ ReconNinja v8.2.1 — 38-phase recon framework for pentesters & bug bounty hunters. Subdomain enum → port scan → web recon → WAF/CORS/JS/cloud bucket detection → GitHub OSINT → CVE lookup → AI threat analysis → HTML report. Domains, IPs, CIDRs, target lists. Plugin system. 598 tests.

slack-watchman

Slack enumeration and exposed secrets detection tool

numasec

AI agent for penetration testing. Like Claude Code, but for security. Open source, MCP-native, works with any LLM.

wfh-wordlist

The most comprehensive wordlist generation toolkit for pentest, red team, and security research. 25 subcommands: charset, profile, corp-users, default-creds, password-dna, DNS fuzzing, web scraping, ISP keygen, ICS/SCADA credentials, ML training, pipal analysis, and more. Python 3.8+ | pip install wfh-wordlist

tempor

Quick and Easy Infrastructure.

fas-judgement

Open-source prompt injection attack console - Test AI systems for prompt injection vulnerabilities

aisploit

🤖🛡️🔍🔒🔑 Tiny package designed to support red teams and penetration testers in exploiting large language model AI solutions.

mcpsafe

Live-runtime security and stress testing for MCP servers — adversarial payloads, load & concurrency, latency, auth bypass. SARIF output.

kcwarden

Keycloak auditor

llamator

Framework for testing vulnerabilities of GenAI systems.

tinman-openclaw-eval

Security evaluation harness for OpenClaw agents - powered by Tinman

gitlab-harvester

Global term search for GitLab via gitlab-python

basilisk-ai

Basilisk — Open-source AI red teaming framework with genetic prompt evolution. Automated LLM security testing for GPT-4, Claude, Grok, Gemini. OWASP LLM Top 10 coverage. 32 attack modules.

colony-probe

Offensive AI red-team tool: multi-turn 'innocent question' sequences for system prompt reconstruction.

pen-tester-agent

A penetration testing agent powered by local LLMs via Ollama

discoursemap

DiscourseMap is a comprehensive security testing framework for Discourse forum platforms. Written for security professionals and forum administrators.