Back
Tool
Codex
Related CVEs
Recent activity
AI-Driven Exploitation of PaperCut Vulnerabilities Compromises 440 Servers GloballyA Russian-speaking threat actor has exploited vulnerabilities CVE-2026-81578 and CVE-2026-82078 in PaperCut NG/MF software, compromising at least 440 instances across 395 organizat…Plugin4Shell: Zero-Click RCE Vulnerability in Major AI Coding AgentsPlugin4Shell is a critical zero-click remote code execution vulnerability affecting four major AI coding agents: Claude Code, Codex, GitHub Copilot, and Gemini CLI. Discovered by A…Critical Ruflo Vulnerability Allows Full Control of AI Agent PlatformsNoma Labs has disclosed a critical vulnerability (CVE-2026-59726) in the Ruflo AI hosting platform, allowing unauthenticated attackers to execute arbitrary commands and take full c…HEIF Heist: Remote Code Execution Vulnerabilities Exploited in Major PlatformsThe HEIF Heist refers to a class of vulnerabilities affecting image-processing libraries like libheif and libde265, allowing attackers to execute remote code through malicious HEIF…Hackers Exploit OpenAI Vulnerabilities Using Anthropic's ClaudeIn July 2026, researchers from Hacktron used Anthropic's Claude AI model to exploit vulnerabilities in OpenAI's community forum, leading to unauthorized access to internal reposito…GitSpawn Vulnerabilities Allow Code Execution in AI Coding AgentsA series of vulnerabilities, termed GitSpawn, have been disclosed affecting multiple AI coding agents, including Claude Code, Codex, and Cursor. These flaws allow malicious Git con…Vulnerabilities in AI Coding Tools Expose GitHub Secrets to AttackersAI coding tools from Anthropic, Google, and OpenAI were found vulnerable to malicious GitHub issues. Researchers at Novee Security identified flaws in Claude Code, Gemini CLI, and …OpenAI Codex Fails to Mitigate Linux Threats During Cyber IncidentA Linux user attempted to use OpenAI's Codex AI agent for incident response during a cyberattack but faced significant challenges. The user was unaware that at least two threat act…GitHub Agentic Workflows Vulnerability Exposes Private RepositoriesIn July 2026, Noma Labs discovered a prompt injection vulnerability in GitHub's Agentic Workflows, named GitLost, allowing unauthenticated attackers to access private repositories …