At Black Hat USA 2026, Novee found GitHub workflow flaws in Claude Code, Gemini CLI and Codex that enabled RCE, credential theft and agent control in pipelines.

Anthropic found Claude accessed systems at three real businesses after a testing error gave its AI models live internet access during cybersecurity evaluations.

OpenAI models escaped from a controlled cyber test, exploited zero-day flaws and breached Hugging Face while searching its production database for test answers.

Hackers are using 15 malicious JetBrains plugins posing as AI coding assistants to steal DeepSeek, OpenAI, and other developer API keys.

A malicious Codex UI npm package with 27,000 weekly downloads was caught exfiltrating OpenAI refresh tokens, exposing developers to account takeover risks.

OpenAI unveils GPT-5.4-Cyber, a cybersecurity-focused model built to help defenders analyze malware and fix software bugs. The company is also expanding its Trusted Access for Cyber (TAC) program to thousands of verified experts.