A shared trust risk has been identified in three AI coding agents - Claude Code, Gemini CLI and Codex - in which malicious GitHub issues can influence subsequent agent runs. Security firm Nobi Security found trust boundaries can break across tool permissions, sandbox isolation and shared workspaces. Researchers said the structure could enable remote code execution, data leaks and persistent control of follow-on agents. Google rated the issue at CVSS 10.0 and adjusted trust mechanisms.

Ninehire, a recruitment management solution operated by Worksphere, has launched an MCP (Model Context Protocol) integration feature that links its platform with external AI tools, the company said on Wednesday. The update enables users to query recruitment data, edit job postings and register applicants through natural-language conversations. It supports AI tools such as Claude Code, Codex and Gemini CLI. The feature is available to enterprise members and above, with dedicated MCP keys issued to workspace administrators.