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

AI-driven vulnerability discovery and live validation

Wireshark-like forensic analysis for Model Context Protocol communications Capture, inspect, and investigate all HTTP requests and responses between…

Modular security toolkit for autonomous agents providing static analysis, configuration auditing, runtime monitoring, and supply chain verification…

Experimental Linux strace LLM agent

Bidirectional token-classification model for PII detection and masking in text, with CLI for redaction, evaluation, and finetuning on-premises.

Security standard for agent skills, providing guidelines and best practices to secure AI-driven autonomous agents in cloud and API environments.

Intentionally vulnerable machine learning model for hands-on security training. Explore common ML vulnerabilities, adversarial attacks, and defensive…

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…

Offline AI Security Assistant for Air-Gapped Pentesting

The most comprehensive LLM + MCP security guide i.e. OWASP aligned, real CVEs, actionable checklists

Free XP on bug bounty, vulnerability scanning by wrapping well maintained tools, to perform automated tests. Alongside AI agents for binary analysis,…

Security scanner for MCP servers. Grades auth, permissions, injection risks, and tool safety. The Lighthouse of agent security.

A Proof-of-concept repository showing how an untrusted MCP server can steal literally everything...

Playbook-based adversary simulation framework that compiles JSON-defined attack paths into position-independent shellcode payloads for validating…

A transparent PII redaction proxy for LLM API traffic. Sits between an application and an LLM provider (currently Anthropic), pseudonymizing…

A minimal LLM-powered zero-day vulnerability scanner by AISLE.

Research code implementing backdoor attack and defense methods for LLMs, including IBSD, SLIP, BeDKD, and BadApex algorithms.

Research pipeline implementing a visual-contextual jailbreak against multimodal LLMs: T2I prompt extraction, SD3.5 image rendering, multi-round spoof…