Just days after the disclosure of the almost perfect 10 vulnerability CVE-2026-19478, hackers are already on the warpath.
Adversa says encrypted prompt injection can make Grok send a user's name, location, tier, and chat prompts to an ...
The type confusion vulnerability allows a guest-to-host sandbox escape which can lead to remote code execution ...
Adversa AI says Grok still leaks user names, location, and full chat history to attackers hiding encrypted commands on a web ...
A critical command-injection flaw in Zimbra Collaboration Suite is being actively exploited, prompting administrators to ...
A newly disclosed critical vulnerabilities across several open-source SAML implementations through an AI-assisted research pipeline using Anthropic’s Claude Opus.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results