pyrit

This bash script will install wifite2 and its other tools Pyrit, bully, wireshark, hcxtools, hcxdumptool, macchanger

Offensive security testing CLI for AI agents — 85 attack strategies (and counting) across 12 categories

It has been developed in order to facilitate the use of ready-made Brute Force tools in Kali-Linux operating systems and is written in Python language.

Projet issu du codelab Devfest Nantes 2025 “La guerre des prompts” : atelier de 2h pour apprendre à pirater des IA et comment les protéger via des frameworks open source

script for simplifying wifite to be easier, quicker, and more effective.

Autonomous AI Red Teaming laboratory validating the Microsoft AI Red Team Taxonomy using the PyRIT framework. Focused on Agentic AI security and strategic conversational persistence.

KYA (Know Your Agents) — Open-source trust, governance, and evidentiary assurance infrastructure for autonomous systems. Built on KYP (Know Your Principal), a unified trust model for human users, AI agents, service accounts, and machine identities.

Pyrit test with Palo Alto Networks AI Runtime Security

Python + SQL toolkit for LLM threat intelligence — flags prompt injection, jailbreaks, and data exfiltration mapped to OWASP LLM Top 10 (2025) & MITRE ATLAS.

Arm any MCP-capable agent to autonomously red-team a target LLM. Microsoft PyRIT exposed as 31 composable MCP tools: attacks, scoring, converters & scenarios

Adversarial testing methodology, attack simulations, and MITRE ATLAS mappings for securing clinical AI and LLM systems.

Automated LLM Security Evaluation Framework

Single-file, fully-local three-layer AI red-team smoke test for LLMs + MCP servers — honest, CI-ready, not a compliance tool.

OWASP GenAI Top 10 vulnerability testing framework for LLMs — fully local, GPU-accelerated, custom guardrails

Production-grade multi-agent AI research platform: LangGraph 4-agent pipeline (Search→Summarize→Write→Verify) through a TensorZero gateway (gpt-4o + Groq fallback), AWS Bedrock guardrails, Redis STM, pgvector LTM, semantic cache, LangSmith scoring, PyRIT red-team tests; Terraform + GitHub Actions CI/CD with observability, retries, and auth.

Continuous automated red-teaming for LLMs and AI agents: adaptive jailbreak discovery (PAIR + TAP + Crescendo), MITRE ATLAS mapping, CI/CD gate, query budgets, webhook alerting. Standard library only.

Adversarial security assessment of a local LLM (TinyLlama) and ML model files — prompt injection, jailbreaks, and Pickle/Joblib RCE, tested with Garak, PyRIT, and Fickling.