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 :
Oct. 23, 2025, 12:46 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | HIGH | [email protected] | ||||
| CVSS 4.0 | HIGH | [email protected] |
Solution
- 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 28 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).
A 6-layer security framework for Claude Code workspaces: prompt injection detection, memory poisoning prevention, secrets scanning, behavioral audit logging, and pre-commit guardrails. Install in 5 minutes.
ai-security claude-code devtools mcp owasp prompt-injection security
Python Shell
Working implementation: cryptographically verified short-lived identities for AI decision authentication — CVE-2025-59536 (Patent Pending US 64/006,746)
🛡️ Security scanner for AI agents. Finds vulnerabilities in MCP servers, agent configs, and tool setups. Written in Rust.
Shell Rust Python HTML
None
Shell
A awesome curated list of security resources, hardening tools, threat research, and governance frameworks specifically for Claude Code
agentic-security ai-security anthropic awesome-list claude-code llm-security mcp-security prompt-injection claude-code-security claude-security
AI Agent Security Middleware — 8-layer defense, DLP data flow, prompt injection detection, zero dependencies. SDK + OpenClaw plugin.
openclaw prompt-injection security ai-agent ai-security llm-security shellward pii-detection agent-security cursor data-exfiltration dlp guardrails langchain ai-firewall ai-safety claude-code mcp mcp-security runtime-security
PowerShell Shell TypeScript JavaScript
None
Offensive MCP server auditor — detects tool poisoning, credential leaks, RCE vectors, SSRF, session hijacking, and supply chain vulnerabilities across stdio, HTTP, and SSE transports.
ai-security llm-security mcp model-context-protocol offensive-security security supply-chain tool-poisoning vulnerability-scanner mcp-security open-source mcpscan
TypeScript JavaScript
Professional PoC for CVE-2025-59536 and related CVEs. Demonstrates an MCP Tool Confirmation Prompt Misrepresentation in Anthropic Claude_Code leading to arbitrary OS command execution.
Python
Open detection standard for AI agent threats. Like Sigma, but for prompt injection, tool poisoning, and MCP attacks. Community-driven -- contributions welcome.
agent-security ai-security llm-security mcp-security owasp prompt-injection sigma-rules threat-detection
TypeScript JavaScript Python Shell
Guarding AI agents from Cloned or Untrusted Content
Python Dockerfile Shell
None
29 detection rules for AI agent threats across 9 attack categories. Like Sigma, but for prompt injection, tool poisoning, MCP attacks, and skill compromise. RFC status.
agent-security ai-security llm-security mcp-security open-source prompt-injection sigma-rules threat-detection
TypeScript
None
TypeScript Dockerfile
Scan cloned repos for malicious AI agent configs before you open them
JavaScript TypeScript
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.
-
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
-
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
-
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
-
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
-
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
-
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
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.
-
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