Claude Code and Gemini CLI Flaws Let a GitHub Issue Reach CI Workflow Secrets
Security researchers at Novee Security have uncovered critical vulnerabilities in AI coding agents from Anthropic, Google, and OpenAI. The flaws allow an…
Tag: Gemini CLI
CVE-2026-12537: Critical OS Command Injection in Gemini CLI
CVE-2026-12537 is a critical OS command injection vulnerability in Google's Gemini CLI container launcher. It allows an unprivileged attacker to execute arbitrary…
Agent Data Injection (ADI) Attack: How AI Agents Can Be Tricked Into Misclicking or Running Attacker Commands
A new class of attack called Agent Data Injection (ADI) has been disclosed by researchers from Seoul National University, the University of…
Cursor Flaw Enables Code Execution via Malicious Cloned Repositories on Windows
A critical vulnerability in Cursor, an AI-powered code editor, allows arbitrary code execution on Windows when a user opens a cloned repository…
Friendly Fire Attack: AI Coding Agents Tricked Into Running Malicious Code
Researchers at the AI Now Institute have published a proof-of-concept attack called 'Friendly Fire' that exploits AI coding agents designed to catch…
Gemini CLI: Critical Command Injection Vulnerability
Gemini CLI is Google's AI coding agent. It had a critical OS command injection vulnerability (CVE-2026-12537) that allowed code execution on CI…
Google Patches Critical Gemini CLI Flaw
Google addressed CVE-2026-12537 in Gemini CLI 0.39.1 and run-gemini-cli 0.1.22. The advisory states the fix affects all Gemini CLI GitHub Actions. Google…