CVE-2026-33068
CVE-2026-33068
7.7
HighPublished:
Last updated:
Source:security-advisories@github.com
Analyzed
Weakness (CWE)
CVSS Vector
v4.0- Attack Vector
- Network
- Attack Complexity
- Low
- Attack Requirements
- Present
- Privileges Required
- None
- User Interaction
- Passive
- Confidentiality (Vulnerable)
- High
- Integrity (Vulnerable)
- High
- Availability (Vulnerable)
- High
- Confidentiality (Subsequent)
- None
- Integrity (Subsequent)
- None
- Availability (Subsequent)
- None
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.
References
security-advisories@github.com
https://github.com/anthropics/claude-code/security/advisories/GHSA-mmgp-wc2j-qcv7