CVE-2025-59536 Claude Code's startup trust dialog could lead to Command Execution attack
HighCVSS 8.7
EPSS 26.3%
- Published
- Updated
- Exploit status
- No public exploit known
- CISA SSVC
- No known exploitation · automatable: no · technical impact: total
Description
Claude Code is an agentic coding tool. Versions before 1.0.111 were vulnerable to Code Injection 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. This issue is fixed in version 1.0.111.
Upgrade path
3 packages: 2 fixed.
| Package | Affected | Fixed in | Status |
|---|---|---|---|
| Anthropic claude code | < 1.0.111 | 1.0.111 | Fixed |
| anthropic-ai @anthropic-ai/claude-code(npm) | < 1.0.111 | 1.0.111 | Fixed |
| anthropics claude-code | = < 1.0.111 | No fix listed | Versions listed |
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| anthropic-ai @anthropic-ai/claude-code(npm) | < 1.0.111 | 1.0.111 |
| anthropics claude-code | = < 1.0.111 | No fix listed |
| Anthropic claude code | < 1.0.111 | 1.0.111 |
References
- https://github.com/anthropics/claude-code/security/advisories/GHSA-4fgq-fpq9-mr3g vendor-advisory
- nvd.nist.gov third-party-advisory vendor-advisory
- github.com
- github.com product