#1LLM security, prompt injection, model extraction, adversarial AI, and AI red teaming tools.
Kitploit recommended

Google Tensor Cracks

🐢 Open-Source Evaluation & Testing library for LLM Agents

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

A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)

A repo for jailbreaking various LLMs, mainly Claude

Autonomous AI pentesting engine, continuous offensive security across web, cloud, AD & Kubernetes. Agentic reasoning + real exploit execution deliver…

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

A GitHub Action invoking the Gemini CLI.

AI-first external attack surface assessment with continuous discovery, evidence-based vulnerability validation, and developer-agent MCP integration.

Proxy server that wraps MCP servers with behavioral profiling, security scanning, risk gating, and safe execution. Detects prompt injection,…

☸️ The Testing Platform for the agentic SDLC

Proper sandboxing for agentic coding and web browsing

The AI Security Verification Standard (AISVS) focuses on providing developers, architects, and security professionals with a structured checklist to…

A secure Python sandbox, written in Rust, for code written by AI.

Open-source, self-hosted security pipeline for IT, AI and OT. Logs in. Evidence out.: OCSF normalization, 46 detection rules…

Programmable guardrails for LLM chat apps: enforce input/output rails, block jailbreaks and prompt injections, detect hallucination, and mask…

Autonomous LLM red team agent that plans and executes full attack chains—recon, exploitation, privilege escalation, lateral movement and C2—inside an…

Autonomous Hacking Agent for Red Team