Cyber Resilience

CVE-2025-58764

RCE in Anthropic Claude Code ≤ 1.0.105

Published
10 September 2025
Modified
24 October 2025
Patch / advisory
CVSS Score v4 8.7
Click a component to see what it means
Raw vectorCVSS:4.0/AV:N/AC:L/AT:N/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 0.0055 43th percentile
Risk Priority 55 floored blend · peak EPSS

Summary

CVE-2025-58764 is a high-severity Code Injection (CWE-94) vulnerability in Anthropic Claude Code. Its CVSS base score is 8.7 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique Command and Scripting Interpreter (T1059); ranked at the 43th 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-2025-58764 is a critical code injection vulnerability (CWE-94) in Claude Code, an agentic coding tool developed by Anthropic. The issue stems from an error in command parsing that allows attackers to bypass the tool's confirmation prompt, enabling the execution of untrusted commands. This affects all versions of Claude Code prior to 1.0.105, with a CVSS v3.1 base score of 9.8 (AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H), indicating high severity due to its network accessibility, low complexity, and lack of required privileges or user interaction.

Exploitation requires an attacker to insert untrusted content into the Claude Code context window, after which the parsing flaw reliably triggers arbitrary command execution on the host system. Any unauthenticated remote attacker capable of influencing the context—such as through malicious inputs in collaborative coding sessions, shared projects, or integrated workflows—can achieve full compromise, including unauthorized access to sensitive data, modification of files, or system disruption.

The official advisory at https://github.com/anthropics/claude-code/security/advisories/GHSA-qxfv-fcpc-w36x confirms that users on standard auto-update channels have received the fix automatically. Those using manual updates must upgrade to version 1.0.105 or later to mitigate the vulnerability, as no additional workarounds are provided.

OWASP Top 10 for Web (2025)

EU & UK References

Vulnerability Data

Claude Code is an agentic coding tool. Due to an error in command parsing, versions prior to 1.0.105 were vulnerable to a bypass of the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires…

more

the ability to add untrusted content into a Claude Code context window. Users on standard Claude Code auto-update will have received this fix automatically. Users performing manual updates are advised to update to version 1.0.105 or the latest version.

CWE(s)

AI Security AnalysisAI

AI Category
Enterprise AI Assistants
Risk Domain
LLM/Generative AI Risks
OWASP Top 10 for LLMs 2025
None mapped
AI-specific weaknesses CR
  • CWE-1427 — Untrusted context input bypasses confirmation via parsing flaw (prompt injection).
Mapped by Cyber Resilience · not in NVD. Poisoning and extraction cases are routed to MITRE ATLAS instead of a synthetic CWE.
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.
T1059.001 PowerShell Execution
Adversaries may abuse PowerShell commands and scripts for execution.
T1059.002 AppleScript Execution
Adversaries may abuse AppleScript for execution.
T1059.004 Unix Shell Execution
Adversaries may abuse Unix shell commands and scripts for execution.
T1059.005 Visual Basic Execution
Adversaries may abuse Visual Basic (VB) for execution.
T1059.006 Python Execution
Adversaries may abuse Python commands and scripts for execution.
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2025-59041Same product: Anthropic Claude Code
CVE-2025-59536Same product: Anthropic Claude Code
CVE-2025-65099Same product: Anthropic Claude Code
CVE-2026-24887Same product: Anthropic Claude Code
CVE-2026-25722Same product: Anthropic Claude Code
CVE-2026-25723Same product: Anthropic Claude Code
CVE-2026-40068Same 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

Affected Assets

anthropic
claude code
≤ 1.0.105

Mitigating Controls

Control response

Prevent
Stop it (NIST 800-53)

Detect
Catch it (NIST detect / respond)

Harden
Shrink the surface (DISA STIG)

Validate
Prove the fix (OWASP ASVS)
  • V1.3.1

Mitigating Controls (NIST 800-53 r5) AI

Developer testing and evaluation finds code paths that accept and execute externally influenced strings.

Input validation directly stops untrusted data from being used to construct executable code without neutralization.

Least privilege limits the damage an injected code fragment can perform once executed.

Requiring documented secure development standards and tools enforces use of safe code-generation APIs and escaping.

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

PR.PS-06's SDLC practices directly target injection flaws via secure coding and testing (mostly), yet as a single broad outcome it leaves many code-generation specifics unaddressed (partial).

PR.DS-10 none match
prevents

PR.DS-10 protects runtime data confidentiality/integrity but has no bearing on neutralizing externally influenced input during code generation, so neither direction shows any preventive effect.

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.

prevents

Banning unapproved code samples and unauthenticated web services, combined with secure-coding standards and SAST, prevents the dynamic generation or inclusion of attacker-supplied code.

none

Controls that restrict unauthorized or malicious code from being introduced via external networks or removable media limit opportunities for an attacker to inject and execute arbitrary code.

References