UKGovernmentBEIS/sandbox_escape_bench

AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assessment, SBOM generation, and static analysis.

Self-contained, Dockerized offensive security challenges for evaluating AI-powered penetration testing agents. Covers modern tech stacks (Node.js, Python, Go, Java, PHP, Ruby) across diverse vulnerability classes and target environments from basic injection to multi-step exploit chains, sandbox escapes, and defense-enabled environments.

Red-teaming and evaluation framework for AI agents, built around an OWASP-inspired ASI01–ASI10 taxonomy

AI model safety scanner built on NVIDIA garak

ExploitBench measures how far AI agents climb, from reaching vulnerable code, to triggering the bug, to building exploit primitives, to arbitrary code execution.

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

CVE-Bench: A Benchmark for AI Agents’ Ability to Exploit Real-World Web Application Vulnerabilities

AI agent benchmark hackability scanner — find evaluation vulnerabilities before they undermine your results

Run safety benchmarks against AI models and view detailed reports showing how well they performed.