AI agent vulnerability · Claude Code

CVE-2025-64755: @anthropic-ai/claude-code has Sed Command Validation Bypass that Allows Arbitrary File Writes

highCVSS 4.0 8.7GHSA-7mv8-j34q-vp7q

Due to an error in sed command parsing, it was possible to bypass the Claude Code read-only validation and write to arbitrary files on the host system. Users on standard Claude Code auto-update will have received this fix automatically. Users performing manual updates are advised to update to the latest version. Thank you to Adam Chester - SpecterOps for reporting this issue!

Published Nov 20, 2025 · Updated Nov 21, 2025

Affected packages

@anthropic-ai/claude-code

Ecosystem: npm
Affected: < 2.0.31
Fixed in: 2.0.31
Check: npm ls @anthropic-ai/claude-code

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

Due to an error in sed command parsing, it was possible to bypass the Claude Code read-only validation and write to arbitrary files on the host system.

Users on standard Claude Code auto-update will have received this fix automatically. Users performing manual updates are advised to update to the latest version.

Thank you to Adam Chester - SpecterOps for reporting this issue!

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More Claude Code vulnerabilities

All Claude Code entries