Sandbox vulnerability gives rogue AI agents a path to escape and leak data, research says
The new research, published by AI security startup AIR, found that a network filtering flaw in Vercel Sandbox — a tool used to run code in isolated environments — could allow agents to exploit certificate validation processes to transmit data outside approved networks.
Excerpt from the primary source: The Record by Recorded Future News
Who is affected
Security professionals
What you should do · Be aware
No immediate action is indicated. Share this with the relevant teams and watch for updates.
Automated guidance based on this story's classification. Check the linked advisories for specifics.
Sources
We link to original and authoritative sources. Headlines and excerpts belong to their publishers.
Related
Windows 11 KB5127648 & KB5126653 cumulative updates released
Microsoft has released Windows 11 KB5127648 and KB5126653 cumulative updates for versions 26H2/25H2/24H2 and 23H2 to fix security vulnerabilities and bugs and add new features.
Adobe Patches 140 Vulnerabilities Across 10 Products
The flaws affect products such as Commerce, Photoshop, ColdFusion, Substance 3D, Dimension, FrameMaker and Bridge.
Ivanti warns of Connect Secure zero-day exploited in attacks
Ivanti urged customers on Tuesday to immediately patch an actively exploited zero-day vulnerability in the Ivanti Connect Secure (ICS) remote access gateway.
Source reporting says attackers are already exploiting this, so exposed Ivanti Connect Secure / EPMM systems are at immediate risk.
Treat this as an emergency.
Docker Hub flaw let attackers impersonate users, tamper with images
Docker has disclosed a critical vulnerability (CVE-2026-105445) in Docker Hub that let attackers access another user's container repositories using a personal access token (PAT).