---
cve: "CVE-2026-33068"
severity: "HIGH"
cvss: 7.7
epss: "34%"
vendor: "anthropics"
kev: false
exploited: false
published: "2026-03-20 09:16:15"
tags: [cve, security, high]
source: tsecurity.de CVE-Dossier
exported: "2026-09-11T00:42:01+02:00"
---

# CVE-2026-33068

> 7.7 HIGH · 🧪 PoC

## Beschreibung

Claude Code is an agentic coding tool. Versions prior to 2.1.53 resolved the permission mode from settings files, including the repo-controlled .claude/settings.json, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set permissions.defaultMode to bypassPermissions in its committed .claude/settings.json, causing the trust dialog to be silently skipped on first open. This allowed a user to be placed into a permissive mode without seeing the trust confirmation prompt, making it easier for an attacker-controlled repository to gain tool execution without explicit user consent. This issue has been patched in version 2.1.53.

## CVSS-Vektor

```
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
```

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

## Patch verfügbar (OSV)

- 6e7f65eb95693516424e3e21b93c700e1a41e069 (Commit)

## Referenzen

- <https://github.com/anthropics/claude-code/security/advisories/GHSA-mmgp-wc2j-qcv7>

---
_Exportiert aus dem [tsecurity.de CVE-Dossier](https://tsecurity.de/cve?cve=CVE-2026-33068) · Datenquellen: EUVD (ENISA), NVD, OSV, CISA KEV, FIRST EPSS, Exploit-DB, BSI BITS_