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

Proof-of-concept that poisons MLflow registered models via the REST API, embedding a malicious pickle to trigger RCE when the model is loaded.

A WordPress plugin exposing an MCP server over the REST API, with the security model as the point -- closes the CVE-2026-15015 OAuth-bypass shape by…

Agentic reverse engineering IDE with a pure-Rust multi-architecture disassembler, native decompiler, debugger, and LLM agent for binary analysis and…

Sandbox for AI coding agents. Runs Copilot CLI, Claude Code, OpenCode, Gemini CLI, Antigravity, Pi, goose or a plain shell inside a kernel-level…

Open reference implementation of the VEP protocol (RFC-010): a deterministic sandbox and benchmark suite evaluating AI agent runtime containment…

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

Self-hosted AI agent harness for authorized pentests, bug bounty, security labs, and CTFs. Plugin-based, multi-provider LLM support with local…

Local AI Capture-the-Flag platform with guided lessons on prompt injection, tool-call abuse, and OSINT against six simulated chatbot personas.

Security research lab — Unauthenticated RCE via insecure deserialization in ComfyUI v0.23.0 (CVSS 9.8). Isolated Docker environment, technical…

Local-first, deterministic MCP server for IDA Pro/Home: 109 strict-schema reverse-engineering operations, evidence-backed findings, and policy-gated…

Open-source antivirus and firewall for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and…

Proof-of-concept and research repository for CVE-2024-37054, an unsafe deserialization flaw in MLflow PyFunc model loading that can lead to remote…

Trained to Escalate: Forensic Analysis and Local Replication of RLHF-Induced Privilege Escalation in AI Agents (CVE-2026-65616)

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

Iterative agent harness that uses LLMs and Certora Prover to generate and refine smart-contract CVL specs, feeding verifier output back until success…

Windows network reconnaissance scanner with ping sweeps, TCP port scanning, and deep AI/ML service detection for finding shadow AI, rogue LLM…

Natural-language Android automation agent that drives real devices via ADB, captures Logcat and screenshots, and exposes an MCP server for AI IDEs…

Forensic Analysis and Local Replication of the OpenAI-Artifactory Privilege Escalation Incident (CVE-2026-65616)