CVE-2025-59536: Claude Code could run project code before the trust dialog
- Product
- @anthropic-ai/claude-code (npm)
- CVE
- CVE-2025-59536
- Affected
- < 1.0.111
- Fixed in
- 1.0.111
Last verified against sources: October 16, 2026
What happened
- According to GitHub Advisory Database's advisory (Oct 3, 2025), a bug in the startup trust dialog meant Claude Code could be tricked into executing code in a project before the user accepted the dialog. [1]
Impact
- Exploitation required the user to start Claude Code in an untrusted directory. [1]
What was done
- Fixed in 1.0.111; users on standard auto-update received the fix automatically. [1]
How to protect yourself
- If you update manually, update to the latest version. [1]
Sources
- GHSA-4fgq-fpq9-mr3g — GitHub Advisory Database
Every statement above was checked against these sources before publishing. Spotted an error? Tell us and we will correct it with a dated note.
Corrections
Report an error or request a correction. We review requests within 5 business days and add a dated correction note.