CVE-2026-55607
Claude Code: Sandbox Escape via Git Worktree Path Confusion Allows Unsandboxed Code Execution
Description
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.
INFO
Published Date :
June 29, 2026, 3:16 p.m.
Last Modified :
June 30, 2026, 4:17 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
Affected Products
The following products are affected by CVE-2026-55607
vulnerability.
Even if cvefeed.io is aware of the exact versions of the
products
that
are
affected, the information is not represented in the table below.
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS | 134c704f-9b21-4f2e-91b3-4a467353bcc0 | |||||
| CVSS 3.1 | HIGH | [email protected] | ||||
| CVSS 4.0 | HIGH | [email protected] |
Solution
- Update Claude Code to version 2.1.163 or later.
- Review and secure git worktree operations.
- Validate repository contents before cloning.
- Restrict access to sensitive user files.
Public PoC/Exploit Available at Github
CVE-2026-55607 has a 3 public
PoC/Exploit available at Github.
Go to the Public Exploits tab to see the list.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-55607.
| URL | Resource |
|---|---|
| https://github.com/anthropics/claude-code/security/advisories/GHSA-7835-87q9-rgvv | Vendor Advisory |
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-55607 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-55607
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Kernel level behavioral security and adaptive memory layer for autonomous coding agents.
Go Makefile C Dockerfile Shell Python
Security boundary CLI proxy between AI coding agents and your shell — redacts secrets, neutralizes prompt injection, wraps untrusted terminal output, and audits every command. Single Rust binary.
ai ai-agents ai-safety claude-code cli command-line-tool devtools llm llm-security prompt-injection proxy rust secret-redaction security shell agentic-ai guardrails rust-cli secrets-detection terminal-proxy
Rust
None
Objective-C C CSS Shell HTML
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-55607 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-55607 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
Initial Analysis by [email protected]
Jun. 30, 2026
Action Type Old Value New Value Added CVSS V3.1 AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H Added CPE Configuration OR *cpe:2.3:a:anthropic:claude_code:*:*:*:*:*:node.js:*:* versions from (including) 2.1.38 up to (excluding) 2.1.163 Added Reference Type GitHub, Inc.: https://github.com/anthropics/claude-code/security/advisories/GHSA-7835-87q9-rgvv Types: Vendor Advisory -
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
Jun. 29, 2026
Action Type Old Value New Value Added SSVC {'id': 'CVE-2026-55607', 'role': 'CISA Coordinator', 'options': [{'exploitation': 'none'}, {'automatable': 'no'}, {'technicalImpact': 'total'}], 'version': '2.0.3', 'timestamp': '2026-06-29T15:51:20.888452Z'} -
New CVE Received by [email protected]
Jun. 29, 2026
Action Type Old Value New Value Added Affected [{'vendor': 'anthropics', 'product': 'claude-code', 'versions': [{'status': 'affected', 'version': '>= 2.1.38, < 2.1.163'}]}] Added Description 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. Added CVSS V4.0 AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X Added CWE CWE-22 Added CWE CWE-78 Added CWE CWE-59 Added Reference https://github.com/anthropics/claude-code/security/advisories/GHSA-7835-87q9-rgvv