anthropics/claude-code · Security
Claude Code can execute commands prior to the startup trust dialog
- GHSA ID
- GHSA-4fgq-fpq9-mr3g
- CVE ID
- CVE-2025-59536
- Severity
- high
- Published
- Updated
- CVSS v4
- 8.7 · CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
Description
Due to a bug in the startup trust dialog implementation, Claude Code could be tricked to execute code contained in a project before the user accepted the startup trust dialog. Exploiting this requires a user to start Claude Code 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 https://hackerone.com/avivdon for reporting this issue!
CWEs
- CWE-94 · Improper Control of Generation of Code ('Code Injection')