Browse / Tool and Agent Misuse / CVE-2025-59828
Claude Code Vulnerable to Arbitrary Code Execution via Plugin Autoloading with Specific Yarn Versions
- Class
- Tool and Agent Misuse (filed by a model that read the advisory)
- Technique
- Code and command execution
- Also involves
- Unsafe Model Loading and Supply Chain
- Affected
- @anthropic-ai/claude-code (npm)
- Gets past
- Approval or confirmation prompt
- CVSS
- CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
- EPSS
- 0.4% chance of exploitation in 30 days
How it works, in short
Claude Code runs yarn --version in untrusted directories, and malicious Yarn config can execute code before the trust dialog is shown. (Our summary, written by a model. The source text is below.)
Details
When using Claude Code with Yarn installed, Yarn config files can trigger code execution when running yarn --version. This could lead to a bypass of the directory trust dialog in Claude Code, as plugins and yarnPath could be executed prior to the user accepting the risks of working in an untrusted directory. 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 Benjamin Faller, Redguard AG and Michael Hess for reporting this issue!
References
- https://github.com/anthropics/claude-code/security/advisories/GHSA-2jjv-qf24-vfm4
- https://nvd.nist.gov/vuln/detail/CVE-2025-59828
- https://github.com/anthropics/claude-code
- https://osv.dev/vulnerability/GHSA-2jjv-qf24-vfm4
- https://www.cve.org/CVERecord?id=CVE-2025-59828
- https://yarnpkg.com/advanced/plugin-tutorial
Source: GitHub Advisory Database, used under CC BY 4.0.