8.8
HIGH CVSS 3.1
CVE-2025-59536
Claude Code's startup trust dialog could lead to Command Execution attack
Description

Claude Code is an agentic coding tool. Versions before 1.0.111 were vulnerable to Code Injection due to a bug in the startup trust dialog implementation. Claude Code could be tricked to execute code contained in a project before the user accepted the startup trust dialog. Exploiting this requires a user to start Claude Code in an untrusted directory. Users on standard Claude Code auto-update will have received this fix automatically. Users performing manual updates are advised to update to the latest version. This issue is fixed in version 1.0.111.

INFO

Published Date :

Oct. 3, 2025, 7:15 a.m.

Last Modified :

June 17, 2026, 9:46 a.m.

Remotely Exploit :

Yes !
Affected Products

The following products are affected by CVE-2025-59536 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.

ID Vendor Product Action
1 Anthropic claude_code
2 Anthropic claude_desktop
CVSS Scores
The Common Vulnerability Scoring System is a standardized framework for assessing the severity of vulnerabilities in software and systems. We collect and displays CVSS scores from various sources for each CVE.
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 1.0.111 or later to fix the code injection vulnerability.
  • Update Claude Code to the latest version.
  • Ensure projects are started in trusted directories.
Public PoC/Exploit Available at Github

CVE-2025-59536 has a 119 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-2025-59536.

URL Resource
https://github.com/anthropics/claude-code/security/advisories/GHSA-4fgq-fpq9-mr3g 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-2025-59536 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-2025-59536 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).

Quill Change Control verifies AI-authored pull requests against a human-signed task boundary and emits a PASS / NEEDS_REVIEW / BLOCK Change Passport for reviewers.

agent-governance ai-agents audit-log change-management ci-cd claude-code code-review cursor python

Shell Python

Updated: 1 day, 9 hours ago
0 stars 0 fork 0 watcher
Born at : July 7, 2026, 10:14 p.m. This repo has been linked 1 different CVEs too.

Static security auditor for Claude Code / MCP config — flags supply-chain, credential, and RCE risk before an agent runs. Offline CLI.

Python

Updated: 1 day, 13 hours ago
0 stars 0 fork 0 watcher
Born at : July 7, 2026, 7:53 p.m. This repo has been linked 1 different CVEs too.

None

HTML Ruby JavaScript Shell

Updated: 4 days, 13 hours ago
0 stars 0 fork 0 watcher
Born at : July 4, 2026, 7:32 p.m. This repo has been linked 3 different CVEs too.

Protocolo de auditoría de seguridad pre-instalación para skills de Claude Code, MCPs y repos de GitHub

Updated: 6 days, 21 hours ago
1 stars 0 fork 0 watcher
Born at : July 2, 2026, 11:31 a.m. This repo has been linked 1 different CVEs too.

Claude-only agent framework

Shell

Updated: 6 days, 6 hours ago
0 stars 0 fork 0 watcher
Born at : June 30, 2026, 12:07 p.m. This repo has been linked 2 different CVEs too.

Claude Code skill (defensive): vet a third-party SKILL.md, its hooks, and the settings.json hook it would register BEFORE you install. Static scan for injection/exfiltration/dangerous commands; returns an ALLOW/REVIEW/BLOCK verdict with the exact lines to remove.

ai-agents anthropic claude claude-code claude-code-skill defensive security skill static-analysis supply-chain claude-code-plugin

PowerShell Shell JavaScript

Updated: 1 week, 2 days ago
0 stars 0 fork 0 watcher
Born at : June 26, 2026, 5:57 p.m. This repo has been linked 1 different CVEs too.

Curated security auditors for the backend stack — Supabase, Firebase, Hasura, Strapi, Directus, Payload, Convex, n8n, Ollama & more. Keyless, active-probe, MIT.

awesome awesome-list baas backend devsecops graphql headless-cms security security-audit vulnerability-scanner

Updated: 2 weeks ago
1 stars 1 fork 1 watcher
Born at : June 21, 2026, 12:32 p.m. This repo has been linked 6 different CVEs too.

Scan a repo's .claude/ config (settings.json hooks, MCP servers, env, allowed-tools) for the RCE & API-key-exfiltration footguns (CVE-2025-59536, CVE-2026-21852) that fire when you clone+open an untrusted repository. Static, zero-dep, local-first.

ai-agents claude claude-code cve devsecops mcp rce security static-analysis supply-chain-security

JavaScript

Updated: 2 weeks, 3 days ago
0 stars 0 fork 0 watcher
Born at : June 21, 2026, 11:50 a.m. This repo has been linked 2 different CVEs too.

None

Makefile Python C HTML

Updated: 2 weeks, 2 days ago
0 stars 0 fork 0 watcher
Born at : June 21, 2026, 1:41 a.m. This repo has been linked 1 different CVEs too.

None

Dockerfile Shell Go

Updated: 3 weeks ago
0 stars 0 fork 0 watcher
Born at : June 18, 2026, 8:19 a.m. This repo has been linked 10 different CVEs too.

None

Batchfile Shell Python JavaScript HTML

Updated: 3 weeks, 4 days ago
0 stars 0 fork 0 watcher
Born at : June 13, 2026, 5 a.m. This repo has been linked 2 different CVEs too.

claude code環境構築用01

Shell JavaScript

Updated: 1 week, 6 days ago
0 stars 0 fork 0 watcher
Born at : June 12, 2026, 6:58 a.m. This repo has been linked 1 different CVEs too.

Deep architectural audit and competitive analysis of AI agentic CLI coding tools: Claude Code, OpenCode, Hermes Agent, Kilo Code / Roo Code. Strengths, weaknesses, failure modes, missing features, and white-space opportunity assessment.

Updated: 3 weeks, 6 days ago
0 stars 0 fork 0 watcher
Born at : June 11, 2026, 3:55 p.m. This repo has been linked 2 different CVEs too.

Active red-teaming for MCP servers. Source analysis + live exploitation + auto-fix. Claude Code plugin.

HTML Shell Python

Updated: 4 weeks, 1 day ago
0 stars 0 fork 0 watcher
Born at : June 7, 2026, 5:34 p.m. This repo has been linked 2 different CVEs too.

Tamper-evident, forward-secret data commitments for Python — sign any decision with a one-shot key, audit it forever. Pure stdlib, zero deps.

Python

Updated: 3 weeks, 4 days ago
1 stars 0 fork 0 watcher
Born at : June 3, 2026, 1:23 p.m. This repo has been linked 1 different CVEs too.

Results are limited to the first 15 repositories due to potential performance issues.

The following list is the news that have been mention CVE-2025-59536 vulnerability anywhere in the article.

  • The Hacker News
Amazon Q Developer Flaw Could Let Malicious Repos Run Code via MCP Configs

A high-severity flaw in Amazon Q Developer let a malicious repository run commands and steal a developer's cloud credentials. The path was short: a developer opens the repo, trusts the workspace, and ... Read more

Published Date: Jun 26, 2026 (1 week, 5 days ago)
  • TheCyberThrone
Claude Code Security vs. OpenAI Codex Security – AI Arms Race

A Technical Comparison for AppSec Engineers | March 2026TL;DRBoth tools launched within two weeks of each other in early 2026. Both use LLM-driven reasoning to find and patch vulnerabilities beyond wh ... Read more

Published Date: Mar 08, 2026 (4 months ago)
  • CybersecurityNews
Claude Code Hacked to Achieve Full RCE and Hijacked Organization API keys

Claude Code Hacked RCE Hijacked Organization API keys Critical vulnerabilities in Anthropic’s Claude Code, an AI-powered command-line development tool. The flaws could allow attackers to achieve Remot ... Read more

Published Date: Feb 27, 2026 (4 months, 1 week ago)
  • CybersecurityNews
New Claude Code Enables Remote Control of Your Terminal Session From Your Phone

Claude Code Remote Control From Phone Anthropic has launched a new “Remote Control” feature for its agentic terminal tool, Claude Code. His capability allows developers to start tasks in their local t ... Read more

Published Date: Feb 26, 2026 (4 months, 1 week ago)
  • CybersecurityNews
Critical Claude Code Vulnerabilities Enables Remote Code Execution Attacks

Claude Code Vulnerabilities A critical security flaw in Anthropic’s Claude Code demonstrates how threat actors can exploit repository configuration files to execute malicious code and steal sensitive ... Read more

Published Date: Feb 26, 2026 (4 months, 1 week ago)
  • The Register
Claude collaboration tools left the door wide open to remote code execution

Security vulnerabilities in Claude Code could have allowed attackers to remotely execute code on users' machines and steal API keys by injecting malicious configurations into repositories, and then wa ... Read more

Published Date: Feb 26, 2026 (4 months, 1 week ago)
  • The Hacker News
Claude Code Flaws Allow Remote Code Execution and API Key Exfiltration

Cybersecurity researchers have disclosed multiple security vulnerabilities in Anthropic's Claude Code, an artificial intelligence (AI)-powered coding assistant, that could result in remote code execut ... Read more

Published Date: Feb 25, 2026 (4 months, 1 week ago)

The following table lists the changes that have been made to the CVE-2025-59536 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.

  • CVE Modified by [email protected]

    Jun. 17, 2026

    Action Type Old Value New Value
    Added Affected [{'vendor': 'anthropics', 'product': 'claude-code', 'versions': [{'status': 'affected', 'version': '< 1.0.111'}]}]
  • CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0

    Jun. 17, 2026

    Action Type Old Value New Value
    Added SSVC {'id': 'CVE-2025-59536', 'role': 'CISA Coordinator', 'options': [{'exploitation': 'none'}, {'automatable': 'no'}, {'technicalImpact': 'total'}], 'version': '2.0.3', 'timestamp': '2025-10-03T13:26:09.204169Z'}
  • Initial Analysis by [email protected]

    Oct. 23, 2025

    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 up to (excluding) 1.0.111
    Added Reference Type GitHub, Inc.: https://github.com/anthropics/claude-code/security/advisories/GHSA-4fgq-fpq9-mr3g Types: Vendor Advisory
  • New CVE Received by [email protected]

    Oct. 03, 2025

    Action Type Old Value New Value
    Added Description Claude Code is an agentic coding tool. Versions before 1.0.111 were vulnerable to Code Injection due to a bug in the startup trust dialog implementation. Claude Code could be tricked to execute code contained in a project before the user accepted the startup trust dialog. Exploiting this requires a user to start Claude Code in an untrusted directory. Users on standard Claude Code auto-update will have received this fix automatically. Users performing manual updates are advised to update to the latest version. This issue is fixed in version 1.0.111.
    Added CVSS V4.0 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
    Added CWE CWE-94
    Added Reference https://github.com/anthropics/claude-code/security/advisories/GHSA-4fgq-fpq9-mr3g
EPSS is a daily estimate of the probability of exploitation activity being observed over the next 30 days. Following chart shows the EPSS score history of the vulnerability.