Vuln in Google’s Antigravity AI agent manager could escape sandbox, give attackers remote code executionCyberScoop·Apr 21, 15:43 UTC · Apr 21, 2026Vulnerability in the wild60
GhostApproval Symlink Flaws Could Let Malicious Repos Run Code in AI Coding AgentsThe Hacker News·Jul 9, 04:27 UTC · Jul 9, 2026VulnerabilityCVE-2026-12958CVE-2026-50549CVE-2026-12957135
Researcher Uncovers 30+ Flaws in AI Coding Tools Enabling Data Theft and RCE AttacksThe Hacker News·Dec 15, 00:00 UTC · Dec 15, 2025VulnerabilityCVE-2025-49150CVE-2025-53097CVE-2025-58335+8 CVEs147
Google AI Threat Defense targets attackers using AI to find flaws fasterHelp Net Security·Jul 9, 05:49 UTC · Jul 9, 2026Vulnerability55
Best practices for AI in open-source workHelp Net Security·Jun 25, 00:00 UTC · Jun 25, 2026Vulnerability30
ThreatsDay Bulletin: SMS Blaster Busts, OpenEMR Flaws, 600K Roblox Hacks and 25 More StoriesThe Hacker News·May 1, 07:21 UTC · May 1, 2026VulnerabilityCVE-2019-0708147