New report outlines the Top 25 MCP vulnerabilities and how attackers could exploit AI agents, plus strategies for defense.

AI browsers can do things for you—but handing personal information over comes with security risks. One of these is a prompt ...

AI agents that can control and read data from an internet browser are also susceptible to obeying malicious text circulating in web content. When he's not battling bugs and robots in Helldivers 2, ...

"Vibe coding" is a phenomenon that curiously differs in definition depending on who you're asking. It's a spectrum of sorts; some use AI tools like ChatGPT to develop programs wholesale, with no ...

Fortra has released patches for a critical-severity vulnerability in the GoAnywhere secure managed file transfer (MFT) ...

Invisible prompts once tricked AI like old SEO hacks. Here’s how LLMs filter hidden commands and protect against manipulation ...

Libraesva patches CVE-2025-59689 after confirmed state-sponsored exploitation; update ESG to avoid command injection.

Attackers are evolving their malware delivery tactics by weaponing malicious prompts embedded in document macros to hack AI ...

Fortra has released security updates to patch a maximum severity vulnerability in GoAnywhere MFT's License Servlet that can be exploited in command injection attacks.

Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now Anthropic has begun testing a Chrome ...