
offensive-ai-compilation
A curated list of useful resources that cover Offensive AI.

A curated list of useful resources that cover Offensive AI.

A privacy-first app that strips AI watermarks from content you own.

The exploit server for out-of-band findings. Point a target at a domain you own. Every HTTP request and every email it sends back lands in a…

Adversary Emulation Framework

Security scanner for AI/ML model files. Detects malicious code, backdoors, and vulnerabilities before deployment

Adversarial image attacks on vision-language web agents, from visual grounding to browser execution

Benchmark and evaluation harness testing whether LLM agents resist malicious instructions hidden in multimodal skill images, with 108 cases across…

Tracker of publicly reported prompt-injection techniques, broken down by delivery method, encoding, and propagation behavior, with confirmed models,…

Empire is a post-exploitation and adversary emulation framework that is used to aid Red Teams and Penetration Testers.

CVE-2026-6765, Test only FormAutofill handlers exposed in Firefox

Crystal port of GodPotato to abuse SeImpersonatePrivilege with indirect syscalls, dynamic API resolution and compile-time string obfuscation. Run…

Ghostsplice repository: PoC for Cross-Channel Trust Fragmentation Attack

CVE-2026-7070 PoC for RDP clipboard hijacking via virtual channel injection; includes simulated server and exploit script for data theft/credential…

Browser PoC demonstrating CVE-2026-2828, a WebGPU timing side-channel that leaks cross-origin iframe pixel values by measuring GPU timestamp-query…

A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion (ACE) and related liminal attack vectors. **Delirium** is not…

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

Research implementation of the Black-Hole Attack that poisons vector database indexes via centrality-driven hubness, with FAISS pipelines and…

Black-box attack framework that hijacks reasoning in agentic retrieval-augmented generation systems by injecting poisoned documents, with support for…