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

Open standard for documenting security-relevant metadata of AI models, including training data provenance, PII risk, known vulnerabilities, and…

End-to-end security audit framework for LLM agents: static AST and taint modeling, attack synthesis, Docker sandbox replay, and deterministic verdict…

Research pipeline for detecting latent indirect prompt-injection exposure signals in agentic LLMs via hidden-state probing, including trace…

Lightweight CLI tool that runs AI coding agents inside isolated Bubblewrap sandboxes with strict filesystem, network, and credential isolation to…

Fix-Like Artifacts With Embedded Defects

The Anti-Virus for AI Artifacts & RAG Firewall. A static analysis tool scanning Models and Notebooks for RCE, Datasets and RAG docs for Data…

CVE-2026-45033 PoC for Claude Code, not Github Copilot. Worked for Haiku 4.5.

Read-only WordPress security scanner for HestiaCP servers. Detects wp2shell compromise indicators (CVE-2026-63030 / CVE-2026-60137) across all hosted…

Benchmark code and interactive results for autonomous network-attack detection by tool-using LLM agents investigating raw PCAPs.

Local AI powered red teamer on a phone

Browser extension that detects PII and sensitive data in AI chats, masks it with placeholders before sending, and restores originals in replies—all…

A prompt injection in a code‑review bot that executes AI‑generated fixes in a sandbox. The sandbox uses a blacklist to prevent dangerous commands,…

Security Advisory: Stored Cross-Site Scripting Via Agent Messages Leading To Session Token Theft (openclaw-dashboard)

AI-driven endpoint governance platform that monitors software usage, applies deterministic policy-based risk classification, and generates structured…

Investigate malicious Windows logon by visualizing and analyzing Windows event log

Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a formal…

LLM agent solving traces, leaderboards, and benchmark results across security CTF and hacking platforms

Embed multiple secret messages in LLM chat token choices using arithmetic/Discop steganographic coders, with bit-exact decoding and steganalysis…