| Mobile Web

Search results for Claude Code Security

AI & Enterprise

‘Comment and Control’ attack can hack Claude Code, Gemini CLI and GitHub Copilot at once

A security engineer disclosed a prompt injection technique dubbed “Comment and Control” that can attack Anthropic’s Claude Code, Google’s Gemini CLI and GitHub Copilot Agent at the same time, SecurityWeek reported. The method manipulates common GitHub content such as comments, PR titles and issue bodies to trick AI agents into running attacker-chosen commands. Tests showed credential and API key theft and data exfiltration. All three companies confirmed the issue and paid bug bounties.

AI & Enterprise

Security hot issue: Leading AI firms step up security push in round two

Moves by leading AI model developers to expand into cybersecurity are gathering pace. Anthropic has rolled out Claude Code Security and an automated code review feature to help block errors and vulnerabilities. OpenAI has unveiled the Codex Security application security agent and announced an acquisition of AI security startup Promptfoo. The article also lists other corporate moves in Korea and abroad, funding rounds, and policy work on security and privacy certification.

AI & Enterprise

OpenAI steps up security push with Codex Security release

OpenAI has launched Codex Security, an AI-based application security agent, Axios reported on March 6. The company said the tool finds vulnerabilities in code repositories, validates them and suggests fixes. Codex Security evolved from Aardvark, a security research agent OpenAI has tested with a small number of customers since last year. OpenAI is making it available as a research preview for enterprise, business and education customers, with a free first month.