News
GhostApproval: Wiz Exposes Symlink Trust Gap Across Six Top AI Coding Agents
Wiz Research discloses GhostApproval — a category-level trust boundary flaw where symlinks trick AI coding agents into writing outside the…
#Vulnerability
Posts tagged #Vulnerability
News
Microsoft Discloses 'AutoJack' AI Agent RCE Chain Targeting AutoGen Studio
What Happened On June 18, 2026, Microsoft Security Response Center (MSRC) published a warning detailing 'AutoJack', a multi-stage…
News
CISA Adds LiteLLM Gateway Command Injection (CVE-2026-42271) to KEV Catalog
TL;DR: CISA has added CVE-2026-42271—a high-severity (CVSS 8.7) command injection vulnerability affecting LiteLLM versions…