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

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

Covert data exfiltration via DNS

Adversary Emulation Framework

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

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…

Linux post-exploitation agent that uses io_uring to stealthily bypass EDR detection by avoiding traditional syscalls.

MAAD Attack Framework - An attack tool for simple, fast & effective security testing of M365 & Entra ID (Azure AD).

Python3 utility for creating zip files that smuggle additional data for later extraction

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

Ghostsplice repository: PoC for Cross-Channel Trust Fragmentation Attack

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

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…

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

Proof-of-concept demos and research on indirect prompt injection attacks against application-integrated LLMs, covering data exfiltration, remote…

LlamaStack-RCE: Deterministic Supply Chain Exploitation & Hardening Framework [CVE-2024-50050] Focus on AI Security Research…