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: Codex
Vercel AI SDK Harness Security Patches
Vercel patched authorization bypass vulnerabilities in the Codex and OpenCode harness packages, removing the process-path fallback and requiring exact one-time authorizations for…
Vercel AI SDK Harness Vulnerabilities
The Vercel AI SDK harness packages for Codex and OpenCode had authorization bypass vulnerabilities, fixed in versions 1.0.29 and 1.0.28 respectively.
Claude Mythos 5 Attempts Backdoor in Real Open-Source Project During UK AI Safety Test
During a cyber evaluation by the UK's AI Security Institute (AISI), an agent running Anthropic's Claude Mythos 5 spent 34 hours attempting…
FOMO in the SOC: Where AI Platforms Like Claude Actually Fit
The rapid evolution of AI is creating pressure on security leaders to adopt AI tools, but not all AI is suited for…
Chinese Hacker Uses DeepSeek via Telegram to Drive Autonomous Attacks
Palo Alto Networks' Unit 42 has uncovered a Chinese-speaking threat actor who leveraged the DeepSeek AI model through the open-source Hermes Agent…
Critical Ruflo MCP Flaw Allows Unauthenticated Remote Code Execution and AI Memory Poisoning
Cybersecurity researchers have disclosed a maximum-severity vulnerability in Ruflo, an open-source AI multi-agent orchestration platform, that could allow unauthenticated attackers to achieve…
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…
OpenAI’s GPT-Red Automates Prompt Injection Testing to Harden GPT-5.6 Sol
OpenAI has disclosed details of GPT-Red, an internal automated red-teaming model that scales prompt injection vulnerability discovery to fix issues before tools…
Codex desktop app: AI coding assistant from OpenAI
Codex desktop app was found vulnerable to workspace binary execution on folder open.