Cyber Resilience

CVE-2026-25722

RCE in Anthropic Claude Code ≤ 2.0.57

Published
06 February 2026
Modified
09 February 2026
Patch / advisory
CVSS Score v4 7.7
Click a component to see what it means
Raw vectorCVSS:4.0/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
EPSS Score 0.0036 29th percentile
Risk Priority 55 floored blend · peak EPSS

Summary

CVE-2026-25722 is a high-severity Improper Input Validation (CWE-20) vulnerability in Anthropic Claude Code. Its CVSS base score is 7.7 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique Command and Scripting Interpreter (T1059); ranked at the 29th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.

This vulnerability is AI-related — categorised as Enterprise AI Assistants; in the LLM/Generative AI Risks risk domain.

The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SI-10 (Information Input Validation) — see the control section below for these in your framework.

Deeper analysis AI-assisted summary

Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.

CVE-2026-25722 is a vulnerability in Claude Code, an agentic coding tool, affecting versions prior to 2.0.57. It arises from inadequate validation of directory changes when paired with write operations to protected folders, linked to CWE-20 (Improper Input Validation) and CWE-78 (Improper Neutralization of Special Elements used in an OS Command). An attacker can use the 'cd' command to navigate into sensitive directories like .claude, bypassing write protections and enabling the creation or modification of files without user confirmation. The flaw carries a CVSS v3.1 base score of 9.1 (AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:H/A:H).

Exploitation requires the ability to inject untrusted content into a Claude Code context window, allowing network-accessible attackers with no privileges or user interaction to conduct the attack with low complexity. Successful exploitation enables high-impact integrity and availability violations, such as unauthorized file writes to protected areas, potentially compromising the tool's security boundaries.

The vulnerability has been patched in Claude Code version 2.0.57. Additional details on the issue and remediation are available in the security advisory at https://github.com/anthropics/claude-code/security/advisories/GHSA-66q4-vfjg-2qhh.

OWASP Top 10 for Web (2025)

EU & UK References

Vulnerability Data

Claude Code is an agentic coding tool. Prior to version 2.0.57, Claude Code failed to properly validate directory changes when combined with write operations to protected folders. By using the cd command to navigate into sensitive directories like .claude, it…

more

was possible to bypass write protection and create or modify files without user confirmation. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window. This issue has been patched in version 2.0.57.

CWE(s)

AI Security AnalysisAI

AI Category
Enterprise AI Assistants
Risk Domain
LLM/Generative AI Risks
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: claude

Related Threats

MITRE ATT&CK Enterprise Techniques

T1059 Command and Scripting Interpreter Execution
Adversaries may abuse command and script interpreters to execute commands, scripts, or binaries.
T1059.003 Windows Command Shell Execution
Adversaries may abuse the Windows command shell for execution.
T1059.004 Unix Shell Execution
Adversaries may abuse Unix shell commands and scripts for execution.
T1059.001 PowerShell Execution
Adversaries may abuse PowerShell commands and scripts for execution.
T1190 Exploit Public-Facing Application Initial Access
Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.
T1036.001 Invalid Code Signature Stealth
Adversaries may attempt to mimic features of valid code signatures to increase the chance of deceiving a user, analyst, or tool.
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2026-25723Same product: Anthropic Claude Code
CVE-2025-64755Same product: Anthropic Claude Code
CVE-2025-54795Same product: Anthropic Claude Code
CVE-2025-55284Same product: Anthropic Claude Code
CVE-2026-24887Same product: Anthropic Claude Code
CVE-2026-55607Same product: Anthropic Claude Code
CVE-2026-39417Shared CWE-20, CWE-78
CVE-2025-34129Shared CWE-20, CWE-78
CVE-2025-54123Shared CWE-20, CWE-78
CVE-2024-23483Shared CWE-20, CWE-78

Affected Assets

anthropic
claude code
≤ 2.0.57

Mitigating Controls

Control response

Prevent
Stop it (NIST 800-53)

Detect
Catch it (NIST detect / respond)

Harden
Shrink the surface (DISA STIG)
  • 6 hardening rules · 3 OS baselines
Validate
Prove the fix (OWASP ASVS)
  • V1.2.5
  • V1.2.8
  • V15.2.5

Mitigating Controls (NIST 800-53 r5) AI

Developer testing and evaluation can discover missing input validation through analysis or test cases.

SI-10 directly requires validity checks on information inputs, structurally preventing improper or missing validation.

Least privilege reduces the permissions available to any process that could be subverted by injected commands.

Least functionality restricts available OS commands and interpreters, limiting the blast radius of injection.

Requiring documented development standards and tools can embed input-validation practices into the engineering process.

Secure engineering principles require proper neutralization of untrusted input before command construction.

Mitigating Controls (NIST CSF 2.0) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.

PR.PS-06 mostly match
prevents

Secure SDLC practices directly require and enforce input validation during development.

PR.PS-02 partial match
prevents

Routine patching/maintenance can remediate known command-injection CVEs in dependencies (partial forward) but does nothing to stop developers from introducing improper neutralization in custom code (none reverse).

Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.

finds

Testing against a defined set of requirements and using code review plus vulnerability scanning forces validation of inputs and handling of unanticipated conditions, reducing the chance that malformed data will be accepted.

prevents

Secure-coding guidelines and mandatory security testing (including code scans) compel developers to validate and sanitize inputs at design and implementation time, lowering the incidence of malformed or malicious data reaching downstream components.

prevents

Mandating input controls that include integrity checks and input validation ensures that untrusted data is examined before use, blocking the root cause of many injection and malformed-data weaknesses.

prevents

Security-by-design principles explicitly call for data validation and sanitization at every layer, reducing the chance that malformed or malicious input will be processed without scrutiny.

prevents

Requiring language-specific secure coding standards, peer review, SAST and documented mitigation of common programming errors forces validation of all inputs before they are trusted.

none

Regular automated validation of system software and data content, combined with scanning of all inbound files, enforces input validation at the boundary before untrusted content is processed.

Hardening callouts derived

Configuration rules from DISA STIG baselines that bear on weaknesses of the type cited by this CVE. Each rule is shown with the relationship its mapping actually records, against the CWE it was authored against. Derived via CVE→CWE over `controls_xwalks` (authoritative rows only; rows rated `none` are excluded).

RHEL 8 (1 rule)
  • V-230265 RHEL 8 must prevent the installation of software, patches, service packs, device drivers, or operating system components of local packages without verification they have been digitally signed using a certificate that is issued by a Certificate Authority (CA) that is recognized and approved by the organization. prevents CWE-20

References