Vulnerability · Published Aug 16, 2025 · Assigned by GitHub_M
CVE-2025-55284Claude Code's Permissive Default Allowlist Enables Unauthorized File Read and Network Exfiltration in Claude Code
High 7.1
In plain English
A high-severity OS command injection in claude-code from anthropics. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.6% (higher than 49% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| npm | @anthropic-ai/claude-code | 1.0.4 | GHSA-x5gv-jw7f-j6xj |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| anthropics | claude-code | < 1.0.4 |
Weakness: CWE-78 · Vector: 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