Code Injection in Claude Code - #VU128528
Published: April 30, 2026
Claude Code
Anthropic
Description
The vulnerability allows a remote attacker to execute arbitrary code.
The vulnerability exists due to improper control of code generation in the startup trust warning mechanism when a user starts Claude Code in a new directory and approves the trust prompt. A remote attacker can place executable files in the folder to execute arbitrary code.
User interaction is required to approve the trust prompt.