← AI agent vulnerabilities

CVE-2026-33068

Claude Code

8.8
Severity
High
Published
March 20, 2026
Last modified
June 17, 2026

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 vector CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Weakness

References

CVE-2026-33068 on NVD

Listed in

HighClaude Code

More Claude Code CVEs

Oct 13
CVE-2026-860637.5

The Claude Code and Claude Desktop plugin installation flow runs git checkout for a marketplace-pinned commit without verifying that the resulting HEAD equals the pinned 40-character SHA.

Oct 7
CVE-2026-1034357.7

Claude Code validated that a target file path resided within the project working directory at permission-check time, but re-resolved the path at write time without repeating that validation.

Sep 30
CVE-2026-1030122.0

Claude Code selected an API key stored by Claude Code, for example from an earlier `/login` or written directly to its configuration, ahead of the user's valid Claude Enterprise or Team sign-in when…

Sep 26
CVE-2026-1005858.0

OpenClaw (npm package `openclaw`) before 2026.7.1 fails to enforce the owner-only authorization requirement for Claude Code permission prompts delivered through the MCP channel bridge.

Aug 14
CVE-2026-499867.1

The Cortex MCP server (`neuro-cortex-memory`), a cross-platform persistent memory MCP, prior to version 3.17.1 treats the `CLAUDE_PROJECT_DIR` environment variable — automatically set by Claude Code to the…

Aug 13
CVE-2026-736148.8

Network-AI ClaudeHookBridge before 5.15.1 truncates the target string to 500 characters before evaluating denyPatterns, while Claude Code executes the full untruncated command.