Claude Code 2.1.52 Bypass Trust Dialog via .claude/settings.json Permissions
CVE-2026-33068 Published on March 20, 2026
Claude Code has a Workspace Trust Dialog Bypass via Repo-Controlled Settings File
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.
Weakness Type
Reliance on Untrusted Inputs in a Security Decision
The application uses a protection mechanism that relies on the existence or values of an input, but the input can be modified by an untrusted actor in a way that bypasses the protection mechanism.
Products Associated with CVE-2026-33068
Want to know whenever a new CVE is published for Anthropic Claude Code? stack.watch will email you.
Affected Versions
anthropics claude-code Version < 2.1.53 is affected by CVE-2026-33068Exploit Probability
EPSS (Exploit Prediction Scoring System) scores estimate the probability that a vulnerability will be exploited in the wild within the next 30 days. The percentile shows you how this score compares to all other vulnerabilities.