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

[🎖️ Honorable Mention in HAIPS @COLM'26] The first benchmark to evaluate how well do LLM agents act in alignment with their assigned authorization…

Trajectory-aware evolutionary search framework for red-teaming LLM agents over MCP servers, generating adversarial prompts to map vulnerability…

Pre-launch security checklist for AI-generated apps (Lovable, v0, Bolt, Cursor). 69 checks covering Supabase RLS, exposed keys, and prompt injection.…

Proof-of-concept exploit for CVE-2025-23266 (NVIDIAScape) targeting NVIDIA AI container runtime. Demonstrates container escape via GPU driver…

Meet Eclipse the only jailbreak that moonwalks around ChatGPT 4o.

Demo showing Claude Opus does not find CVE-2023-0266

WordPress security scanner with AI-powered analysis, ethical compliance framework, and professional reporting.

Security gateway for MCP servers with per-tool policy enforcement, Ed25519-signed audit receipts, and shadow-mode logging. Supports Cedar, OPA, and…

Research pipeline that constructs verified successful experiences and organizes them into formation records to progressively poison model skills via…

We asked 6 AIs about their own programming. All 6 said jailbreaking will never be fixed. Run it yourself — $2, 10 minutes.

A benchmark for evaluating AI agents on fixing real-world security vulnerabilities.

Research code for red-teaming AI auto-mode monitors, including simulation evals, fuzzing, and monitor implementations for Claude Code and Codex…

Curated collection of research papers on retrieval-augmented generation security, organized by the SLOT taxonomy covering knowledge poisoning,…

Hashcat rule analyzer and interpreter - A Rosetta Stone for decoding hashcat rule syntax

Audit log and secret scanner for AI coding agents: see what Claude Code, Codex, Gemini CLI and 27 more ran on your machine, and find API keys leaked…

Static analysis CLI that scans AI-generated code for vulnerabilities like SQL injection, unsafe reflection, and hardcoded secrets, with SARIF export…

Go-based MITM HTTP/HTTPS proxy with HTTP/2 and HTTP/1.1 interception, local CA/per-host cert generation, CONNECT/WebSocket tunneling, disk caching,…

[NeurIPS '25] Code for Paper "IF-Guide: Influence Function-Guided Suppression of Harmful Training Data for Reducing LLM Toxicity"