
llm-guard
The Security Toolkit for LLM Interactions

Real-time deepfake toolkit for penetration testing of identity verification and video conferencing systems. Supports face swap, image animation, and…

Purple-team telemetry & simulation toolkit.

Research-only AI watermark robustness toolkit: local reverse proxy strips C2PA/EXIF/XMP, Unicode, image/audio stego, OOXML/PDF metadata, and scans…

An Open-Source Package for Textual Adversarial Attack.

AI / LLM Red Team Field Manual & Consultant’s Handbook

PoCs and tools for investigation of Windows process execution techniques

Tools and PoCs for Windows syscall investigation.

Framework for auditing machine learning algorithms against adversarial attacks and biases, providing educational tools and an academic paper to…

A curated list of AI Security materials and resources for Pentesters, Bug Hunters, and Security Researchers.

Hands-on AI security lab platform with 50+ scenarios across prompt injection, agentic system exploitation, model manipulation, and MCP trust boundary…

Evaluation framework that tests whether large language models follow invisible Unicode-encoded instructions embedded in normal-looking text, with…

Two-stage prompt-injection and jailbreak detector: regex gates plus a quantised DeBERTa-v3 ONNX classifier, with image, document, and audio support.…

Automated Adversary Emulation Platform

We asked 6 AIs about their own programming. All 6 said jailbreaking will never be fixed. Run it yourself — $2, 10 minutes.

A repo for jailbreaking various LLMs, mainly Claude

AI Red Teaming playground labs to run AI Red Teaming trainings including infrastructure.

Open-source prompt injection attack console. Test AI security by firing categorized attacks at any endpoint.