OS Command Injection in Claude Code - CVE-2025-55284
Published: April 30, 2026
Claude Code
Anthropic
Description
The vulnerability allows a remote attacker to disclose sensitive information.
The vulnerability exists due to improper neutralization of special elements used in an os command in the safe command allowlist and confirmation prompt handling when processing untrusted content in a Claude Code context window. A remote attacker can add untrusted content to the context window to disclose sensitive information.
Exploitation can bypass confirmation prompts to read a file and send its contents over the network without user confirmation.