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

AI-powered penetration testing assistant using local LLM on linux (Parrot OS)
Security gateway for MCP servers with per-tool policy enforcement, Ed25519-signed audit receipts, and shadow-mode logging. Supports Cedar, OPA, and…

Purple Team Exercise Framework

Code for ACL 2026 (main) paper "DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation"

AI Prompt Secret Scanner: local proxy and Claude Code hook that blocks secrets before they reach AI APIs

Check if your AI agent setup is vulnerable to CVE-2026-33579

HopLa Burp Suite Extender plugin - Brings AI capabilities, autocompletion support, and a set of useful payloads to Burp Suite

Causal context attribution and rule-based monitor LLM defense against indirect prompt injection in LLM agents, achieving state-of-art performance on…

Runtime protection for AI agents

Open security research on AI coding agent infrastructure. Agent-executable remediation manifests for CVE-2026-22812 and CVE-2026-22813.

Enterprise AI agent security toolkit providing pre-flight auditing, configuration hardening, runtime threat detection, and active defense against…

Semantic Observability for UNIX Systems - A lightweight C-based system prober with AI-powered analysis

CVE-2025-31337 Security Advisory - Critical Buffer Overflow in AI Chatbot Framework

CVE-Factory

Automated bug bounty & recon framework — wraps Subfinder, Naabu, Httpx, Nuclei, Nmap, CVEMap, Gowitness, Katana & more behind a unified web UI

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

Silent dependency injection through AI documentation pipelines. 240 isolated Docker runs proving Context Hub's zero-sanitization MCP server lets…