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

AI chat-box pentesting tool in C: fires language (SQLi/NoSQL/XSS/SSTI) and prompt injection payloads at chat interfaces and flags the ones that bite

Sentinel — DeanWay Labs' inbound governor. Guards what an AI agent hears: world content is data, never orders. The mirror of QuietOS.

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord,…

Local-first AI red team for web, API, and LLM application security. Attacker-style reasoning, evidence-backed findings, and skills for AI coding…

DugganUSA threat-intelligence contributions to the IETF Hackathon: real-world agentic-attack benchmark vectors, CVE-2026-33697 attestation analysis,…

An autonomous red-teaming engine for LLMs. RedThread manages the full security lifecycle: generating adversarial attacks, executing precision…

Proof-of-concept and patch for CVE-2026-57845: pickle deserialization RCE in Hugging Face datasets' pandas builder, with reproduction script and…

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

Security research on context compaction in coding agents: shows how forged role labels in untrusted content survive summarization and get executed,…

An audit-oriented risk model for how agent-generated inferences can change epistemic status, gain operational authority, and influence later…

Next-generation JavaScript identifier recovery with LLMs.

Example AI-agent taskflows and MCP servers for auditing source code, triaging issues, and detecting vulnerabilities across web, Android, and iOS…

Burp Suite extension that adds built-in MCP tooling, AI-assisted analysis, privacy controls, passive and active scanning and more

eBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via…

Runtime guard skill that detects and blocks malicious skill-induced attacks in skill-augmented agents, with an MCTS loop that evolves the guard…

Fork optimizado de Bytebot: Agente de IA para control de escritorio. Reducido de 7GB a 1.09GB, parcheada CVE-2026-78250, con documentación viva…

OWASP project for AI-assisted threat modeling, helping teams identify, analyze, and document security threats and mitigations in system designs.

Research code for measuring jailbreak attack success rates (ASR and stepwise ASR) against LLMs, with implementations of attacks such as GCG and…