---
cve: "CVE-2025-59536"
severity: "HIGH"
cvss: 8.7
epss: "33.2%"
vendor: "anthropics"
kev: false
exploited: false
published: "2025-10-03 07:15:44"
tags: [cve, security, high]
source: tsecurity.de CVE-Dossier
exported: "2026-09-10T10:57:42+02:00"
---

# CVE-2025-59536

> 8.7 HIGH · 🧪 PoC

## Beschreibung

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.

## CVSS-Vektor

```
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
```

| Metrik | Wert | Bewertung |
|---|---|---|
| AV Angriffsvektor | Netzwerk | bad |
| AC Komplexität | Gering | bad |
| PR Privilegien | Keine | bad |

## Referenzen

- <https://github.com/anthropics/claude-code/security/advisories/GHSA-4fgq-fpq9-mr3g>

---
_Exportiert aus dem [tsecurity.de CVE-Dossier](https://tsecurity.de/cve?cve=CVE-2025-59536) · Datenquellen: EUVD (ENISA), NVD, OSV, CISA KEV, FIRST EPSS, Exploit-DB, BSI BITS_