Critical vulnerabilities in Anthropic's Claude Code enable remote code execution and API key theft
Check Point Research discovered critical vulnerabilities in Anthropic's Claude Code that allow remote code execution and API key theft through malicious project configurations. The flaws were patched by Anthropic before public disclosure.
What happened
Check Point Research discovered critical vulnerabilities in Anthropic's Claude Code that allow attackers to achieve remote code execution and steal API credentials through malicious project configurations.
The vulnerabilities exploit configuration mechanisms including Hooks, Model Context Protocol (MCP) servers, and environment variables to execute arbitrary shell commands and exfiltrate Anthropic API keys when users clone and open untrusted repositories.
Anthropic patched all reported vulnerabilities prior to public disclosure.
Reported impact
Stolen Anthropic API keys posed enterprise-wide risk, particularly in shared workspaces where a single compromised key could expose, modify, or delete shared files and resources and generate unauthorized costs.
The vulnerabilities could be triggered simply by cloning and opening an untrusted project, bypassing trust controls and executing hidden shell commands without user consent.
Index analysis
Claude Code combines automated code generation with the risks of executing AI-generated commands and sharing project configurations across collaborative environments, introducing novel attack surfaces not addressed by traditional security models.
The platform supports file modifications, Git repository management, automated testing, build system integration, MCP tool connections, and shell command execution, expanding its attack surface.
Governance controls
Anthropic collaborated with Check Point Research to remediate the vulnerabilities prior to public disclosure.
Classification
Sources and evidence
This record was researched and written by the Index, based on the following original reporting.