CVE-2025-55284: Claude Code's Permissive Default Allowlist Enables Unauthorized File Read and Network Exfiltration in Claude Code
Claude Code is an agentic coding tool. Prior to version 1.0.4, it's possible to bypass the Claude Code confirmation prompts to read a file and then send file contents over the network without user confirmation due to an overly broad allowlist of safe commands. 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.
Other sources
Due to an overly broad allowlist of safe commands, it was possible to bypass the Claude Code confirmation prompts to read a file and then send file contents over the network without user confirmation. 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 https://hackerone.com/wunderwuzzi23 for reporting this issue!
— GitHub
Affected Software
Event History
Frequently Asked Questions
What is the severity of CVE-2025-55284?
CVE-2025-55284 is of medium severity as it allows unauthorized access to file contents over the network.
How do I fix CVE-2025-55284?
To fix CVE-2025-55284, update Claude Code to version 1.0.4 or later to prevent the bypass of confirmation prompts.
What versions are affected by CVE-2025-55284?
CVE-2025-55284 affects versions of Claude Code prior to 1.0.4.
What type of vulnerability is CVE-2025-55284?
CVE-2025-55284 is a command injection vulnerability that allows file content to be read and transmitted without user consent.
Who is the vendor for CVE-2025-55284?
The vendor for CVE-2025-55284 is Claude Code.