CVE-2025-54795: Claude Code echo command allowed bypass of user approval prompt for command execution
Claude Code is an agentic coding tool. In versions below 1.0.20, an error in command parsing makes it possible to bypass the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window. This is fixed in version 1.0.20.
Other sources
Due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window.
Users on standard Claude Code auto-update received this fix automatically after release. Current users of Claude Code are unaffected, as versions prior to 1.0.24 are deprecated and have been forced to update.
Thank you to Elad Beber (Cymulate) for reporting this issue!
— GitHub
Affected Software
Event History
Frequently Asked Questions
What is the severity of CVE-2025-54795?
CVE-2025-54795 is rated as a high severity vulnerability due to its ability to bypass security checks and execute untrusted commands.
How do I fix CVE-2025-54795?
To fix CVE-2025-54795, users should upgrade to version 1.0.20 or later of the @anthropic-ai/claude-code package.
What is the exploit path for CVE-2025-54795?
Exploitation of CVE-2025-54795 requires the attacker to introduce untrusted content into a Claude Code context window.
Who is affected by CVE-2025-54795?
CVE-2025-54795 affects users of the @anthropic-ai/claude-code package prior to version 1.0.20.
Is there a workaround for CVE-2025-54795?
There are no specific workarounds documented for CVE-2025-54795; upgrading to the latest version is advised.