CriticalVulnerabilityLLM-specific

CVE-2026-25722: Claude Code write protection bypass via cd into protected directories

Source: NVD(opens in a new tab)
Identifier: CVE-2026-25722
Published: February 6, 2026
Record updated: October 9, 2026

Affected: @anthropic-ai/claude-code < 2.0.57
Fixed in: 2.0.57
released December 2, 2025, 65 days before disclosure
Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.5%

Summary

Claude Code, an agentic coding tool, failed to properly validate directory changes before version 2.0.57. Using the cd command to enter protected directories such as .claude let an attacker bypass write protection and create or modify files without user confirmation. Reliable exploitation required the ability to add untrusted content into the Claude Code context window.

Mitigation

This issue has been patched in version 2.0.57.

Details

Scores and exploitation

CVSS score: 9.1(critical)
Patch available: Yes
EPSS: 0.5%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 4, 2026.

Weaknesses and techniques

Weakness (CWE): CWE-20
CWE-78
Attack pattern (CAPEC): CAPEC-88

Affected

Packages: @anthropic-ai/claude-code@< 2.0.57 (fixed: 2.0.57)
Vendors: Anthropic

Classification

Attack type: Other
Attack sophistication: Moderate
AI component targeted: Agent
Impact: Integrity
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-25722

First tracked: February 15, 2026 at 08:52 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 90% (self-assessed)

Topics

AI agents

Summary

Mitigation

Topics

Related items