Multimodal Safety Is Asymmetric: Cross-Modal Exploits Unlock Black-Box MLLMs Jailbreaks

Multimodal large language models MLLMs have demonstrated significant utility across diverse real-world applications. But MLLMs remain vulnerable to jailbreaks, where adversarial inputs can collapse their safety constraints and trigger unethical responses. In this work, we investigate jailbreaks i...

Exploit for OS Command Injection in Gnu Bash

This is an extension for Burp Suite, a web application security testing tool. The extension, named "ActiveScan++", extends Burp's active and passive scanning capabilities to identify application behavior that may be of interest to advanced testers. It includes checks for potential host header...