Skip to content
AI AgentHigh

CVE-2026-55607: Claude Code is an agentic coding tool. From 2.1.38 until 2.1.163, Claude Code's worktree handling a…

Occurred
Jun 29, 2026
Published
Jun 29, 2026
Source
NVD CVE

Summary

Claude Code is an agentic coding tool. From 2.1.38 until 2.1.163, Claude Code's worktree handling allowed creation of worktrees named ".git" and navigation to worktrees outside the sandbox context, enabling git directory confusion attacks. By exploiting symlink manipulation and git fsmonitor execution during worktree operations, an attacker could overwrite files in the user's home directory (such as .zshenv), leading to code execution outside of seatbelt sandbox restrictions. Reliably exploiting this required the user to clone a malicious repository containing prompt injection content and run Claude Code against it. This vulnerability is fixed in 2.1.163.

Tags

  • CVE
  • CVE-2026-55607
  • cvss:HIGH
  • agent-fail:injection-direct
  • agent-fail:authorization
  • agent-cause:missing-guardrail

Classification

Category confidence: 95%
Severity confidence: 90%

Rationale: Agentic coding tool vulnerability allows sandbox escape and code execution via prompt injection and symlink manipulation.

Classifier: Qwen/Qwen3.5-35B-A3B-FP8

Visit source