# CVE-2026-33068

## Summary

- **CVE ID:** CVE-2026-33068
- **Severity:** HIGH
- **CVSS Score:** 7.7 (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)
- **CWE:** CWE-807
- **Published:** Mar 20, 2026
- **Last Modified:** Mar 20, 2026

## Description

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.

## Affected Products

- anthropics — claude-code (< 2.1.53)

## References

- [CNA](https://github.com/anthropics/claude-code/security/advisories/GHSA-mmgp-wc2j-qcv7)

## Exploitation Prediction (EPSS)

- **EPSS Score:** 0.34%
- **EPSS Percentile:** 26.8

---
_Exported from OnDuty AI Vulnerability Intelligence on 2026-09-11._