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

Reproduction harness, patches and analysis tools for auditing a learned cyber-defense benchmark: captures agent traces, runs red-agent ablations, and…

This repository contains a tool that can be used for automated pentesting tasks.

LLM-driven multi-agent framework that autonomously replicates human penetration testing workflows, orchestrating Kali Linux tooling and RAG knowledge…

Helping Ethical Hackers use LLMs in 50 Lines of Code or less..

Open-source, self-hosted web pentesting suite with agentic scanning, analyst tools, API testing, model checkpoints and MCP integrations.

Multi-agent LLM system that autonomously assesses web application security, orchestrating tool-grounded execution and validating exploits end to end.

Red Team AI Benchmark: Evaluating LLMs for authorized offensive-security tasks

Everything for pentest. | 渗透测试知识库,以 AI Agent 可执行的格式沉淀安全方法论。

Local AI-assisted threat intelligence pipeline that ingests web, RSS and document sources, extracts quote-verified claims, and maps adversary…

Local test range for agent memory poisoning - watch a planted memory steer an agent, then prove the repair. Synthetic targets, scripted deterministic…

CVE-2026-4372: Threat Model, Root-Cause Analysis, Replication & Detection

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

Benign, self-contained reproduction of CVE-2026-77521 (MaxKB prompt-injectable command execution)