ReversingLabs

2 weeks ago | reversinglabs.com | John Mello

Virtual machines (VMs) have become ubiquitous in the enterprise by offering flexibility, scalability, and cost savings. But widespread adoption has outpaced traditional security controls, which often rely on runtime access or agent-based monitoring. Dan Petrillo, vice president of product marketing at ReversingLabs (RL), said in a recent webinar that VMs can be blind spots for threats, exposing organizations to malware, vulnerabilities, supply chain risks, and compliance gaps.

3 weeks ago | reversinglabs.com | John Mello

Software bills of materials (SBOMs) have become a hot topic recently — for a number of reasons. High-profile attacks on software supply chains have exposed the need for organizations to know what third-party and open-source components are in the applications they use. SBOMs are seen as an essential first step on that journey.

3 weeks ago | reversinglabs.com | Todd R. Weiss

The fledgling Model Context Protocol standard has generated lots of headlines and discussion among developers, who like that MCP makes it easy to connect large language models (LLMs) directly with tools and data. The question is whether development teams and organizations are aware of the risks.

1 month ago | reversinglabs.com | John Mello

While the shortest distance between two points is a straight line, a straight-line attack on a large language model (LLM) isn't always the most efficient — and least noisy — way to get the LLM to do bad things. That's why malicious actors have been turning to indirect prompt attacks on LLMs to carry out attacks. Indirect prompt injection attacks occur when malicious instructions are embedded within external content — documents, web pages, or emails — that an LLM processes.

1 month ago | reversinglabs.com | John Mello

Despite the risks associated with artificial intelligence (AI) coding, developers remain enthusiastic, using it to keep up with the demand for delivery software at speed. A recent GitHub survey found that 92% of U.S.-based developers are using AI coding regularly. But while many developers are using AI to assist them in writing code, they seem to be doing so warily.