Tag: claude-code

All the articles with the tag "claude-code".

• Weekly Roundup: A $600K credential leak and three ways to own a coding agent

  4 Sep, 2026

  METR's stolen API key, ransomware crews running Cursor Agent, and a run of coding-agent flaws that fire before the trust prompt does.

• [AUTO] Malicious git configs execute code before approval

  2 Sep, 2026

  AI coding agents run code from .git/config during startup before showing trust prompts.

• [AUTO] Claude Code Auto Mode vulnerable to module shadowing attack

  29 Aug, 2026

  Researcher shows Claude Code Auto Mode vulnerable to 60-80% RCE via module shadowing.

• [AUTO] Coding agents leak secrets through pre-approved tools

  7 Aug, 2026

  Novee Security research reveals critical flaws in Claude Code and Gemini CLI that let attackers reach CI secrets through allowlisted tool features.