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

Professional PoC for CVE-2025-59536 and related CVEs. Demonstrates an MCP Tool Confirmation Prompt Misrepresentation in Anthropic Claude_Code leading…

This technical research and review is for educational purposes on public code and constitutes Fair Dealing under the Copyright Act (Canada).

Proof-of-concept exploit for CVE-2025-32434, a pickle deserialization vulnerability in PyTorch's weights_only mode, demonstrating malicious tar file…

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

Exploit for CVE-2026-33017, an unauthenticated RCE in Langflow 1.8.1 via the build_public_tmp endpoint, enabling Python code injection through…

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


Code repository for CS5446 project exploring defenses against jailbreak attacks on large-language models it includes datasets, notebooks,…

Automated threat hunting pipeline that ingests Azure logs, uses LLM reasoning to detect suspicious activity, assess risk, and generate remediation…

Black-box test whether an LLM chatbot is vulnerable to markdown/HTML exfil (CVE-2025-32711 class). Spins up a sink, sends payloads, renders in…

Educational Python target range simulating CVE-2026-22807, an AI supply chain RCE via TOCTOU in model loading. Includes vulnerable library, PoC…

Artefacts for blog post on finding CVE-2025-37899 with o3

AI powered security analysis extension for Mobile Security Framework MobSF

CAWODOG is a proof-of-concept project demonstrating how to protect Python-based AI models deployed on offline industrial machines. Across three…

My manifesto, and stories, images, and phun stuff

Demonstrates AI agent-driven CVE remediation with cryptographic provenance tracking, showcasing detection, analysis, human approval, and verification…

Modern cyber range with 50 hands-on challenges across web, API, cloud, AI, and blue-team security tracks. Features guided attack chains, transparent…

Exploit for Langflow AI Remote Code Execution (Unauthenticated)