Tools

loosehose/dutchoven

Application-scoped Windows network brownouts in native C and BOF form

telefonica/omlasp

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

adpunisher/ownershipstealer

Command-line utility for Windows that enables SeTakeOwnershipPrivilege and modifies file ownership to the current user, granting access to otherwise…

owasp/ai-vulnerabilities-playground

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

leviticus-triage/cerebro-red-v2

CEREBRO-RED v2: Advanced LLM Red Team Research Platform with PAIR Algorithm and LLM-as-a-Judge Evaluation

zjuicsr/deeptrap

Security benchmark for evaluating OpenClaw agents against adversarial execution contexts including poisoned files, injected skills, misleading tool…

pppyb/secopd

Research implementation for mitigating adaptive prompt injections via on-policy distillation, with training recipes and evaluators for SEP, PISmith,…

xuyw-seu/packetpatch

Practical black-box adversarial packet generation against encrypted traffic classification with minimal overhead and full packet recoverability.

wang-yanting/agentwatcher

Causal context attribution and rule-based monitor LLM defense against indirect prompt injection in LLM agents, achieving state-of-art performance on…

mamadou-keita/deeclip

Implementation of paper "DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images"

jackpurcell/autoran-public

Automated framework for hijacking safety reasoning in large reasoning models via simulated reasoning traces and iterative prompt refinement to…

jinxhy/awesome-moai-security

Curated reading list and taxonomy of attack and defense research for mobile on-device AI systems, covering adversarial, backdoor, model stealing, and…

george0papasotiriou/cve-2026-1337-ai-coding-assistant-prompt-injection-to-sandbox-escape

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,…

sej2020/manipulating-web-agents

Research demonstration of indirect prompt injection attacks to control autonomous LLM-based web agents, with tools for trigger optimization and…

rakib-nyc/nullorigin

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

borealisai/stepjack

Benchmarking framework for evaluating computer-use AI agents against multi-step indirect prompt injection, with automatic adversarial goal…

canonicalmg/reverse-captcha-eval

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

cenobyte-vincit/xspawn

Spawns macOS programs through launchd's private XPC interface without execing them, making EDR record launchd as parent. Supports one-shot,…