← AI agent vulnerabilities

CVE-2026-39861

Claude Code

10.0
Severity
Critical
Published
April 21, 2026
Last modified
June 17, 2026

Claude Code is an agentic coding tool. Prior to version 2.1.64, Claude Code's sandbox did not prevent sandboxed processes from creating symlinks pointing to locations outside the workspace. When Claude Code subsequently wrote to a path within such a symlink, its unsandboxed process followed the symlink and wrote to the target location outside the workspace without prompting the user for confirmation. This allowed a sandbox escape where neither the sandboxed command nor the unsandboxed app could independently write outside the workspace, but their combination could write to arbitrary locations, potentially leading to code execution outside the sandbox. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window to trigger sandboxed code execution via prompt injection. Users on standard Claude Code auto-update have received this fix automatically. Users performing manual updates are advised to update to version 2.1.64 or later.

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

Weakness

References

CVE-2026-39861 on NVD

Listed in

CriticalClaude CodePath traversal

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.