← back
CVE-2025-55284

Claude Code's Permissive Default Allowlist Enables Unauthorized File Read and Network Exfiltration in Claude Code

CVSS 7.1 HIGHEPSS 0.4%CWE-78
In short

Claude Code before version 1.0.4 had overly permissive default settings that allowed an attacker to read files and send their contents over the network without asking the user for permission. This matters because it could expose sensitive data if someone tricks the tool into processing malicious instructions.

Technical detail

A command allowlist bypass in Claude Code versions prior to 1.0.4 permits arbitrary file read and exfiltration via network operations without user confirmation. The attack requires injection of untrusted content into the Claude Code context window; successful exploitation results in unauthorized access to file contents and potential data exfiltration. The vulnerability stems from an overly broad safe command allowlist that failed to properly restrict file and network operations.

Summary generated and translated by AI from the official description.
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.
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N
Affected products
anthropics · claude-code

Want to know if your infrastructure is exposed to this?

Talk to TrueHacking →