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

Secure runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.

AI-powered Docker security scanner that explains vulnerabilities in plain English. An OWASP Lab Project.

OpenMed < 1.5.2 unauthenticated RCE via PII privacy-filter model loading and trust_remote_code=True

Safety cannot be a prompt instruction. TBP provides an external execution-layer boundary for autonomous agents, enforcing hard F/I/W invariants via…

A comprehensive guide to adversarial testing and security evaluation of AI systems, helping organizations identify vulnerabilities before attackers…

Deploy self-hosted AI coding agents (OpenClaw, Claude Code, Codex) into your AWS account with CloudFormation, IAM profiles, and sandbox isolation for…

a fully autonomous AI agent for reverse engineering

LLM-driven agentic group shilling attack framework that manipulates black-box collaborative-filtering recommender rankings using adaptive multi-role…

Cryptographically signed delegation receipts for AI agents. Define exactly what an AI can and can't do — signed, verifiable, tamper-proof.

Lightweight evaluation harness for RAG poisoning defenses that builds four-condition clean/poisoned records and reports prevented targets, net…

Research code for training adapters that make LLM agent backdoors survive benign fine-tuning, with trigger-rate scoring, SWE-bench evaluation, and…

Powerful protection for AI agents - Open-source security and cost tracking for AI applications

Jailbreak vulnerability across early-exit depths LLMs. Published at NeurIPS 2026 in the FLMSec workshop

Offline SAST/DAST triage engine that parses source code and replays HAR traffic to detect business-logic flaws, BOLA, race conditions, and privilege…

How AI turns password attacks from blind enumeration into adaptive campaigns - and the detection rules and countermeasures that stop them. Research…

Open .eml test set for evaluating how email security controls and AI mailbox assistants handle indirect prompt injection across disclosure,…

Autonomous multi-agent AI penetration-testing engine: a governed tool sandbox, an immutable evidence-and-validation gate, and a reproducible…

Red-teaming benchmark and black-box attack framework for evaluating visual misinformation risks in commercial image generators, with 10k false-claim…