CVE-2026-21852

published 21 Jan 2026 · updated 21 Jan 2026

Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation

6.8MediumCVSS 5.3EPSS 28%1 public exploits

A public exploit exists; no exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 28%. No fixed version is recorded.

Claude Code is an agentic coding tool. Prior to version 2.0.65, vulnerability in Claude Code's project-load flow allowed malicious repositories to exfiltrate data including Anthropic API keys before users confirmed trust. An attacker-controlled repository could include a settings file that sets ANTHROPIC_BASE_URL to an attacker-controlled endpoint and when the repository was opened, Claude Code would read the configuration and immediately issue API requests before showing the trust prompt, potentially leaking the user's API keys. Users on standard Claude Code auto-update have received this fix already. Users performing manual updates are advised to update to version 2.0.65, which contains a patch, or to the latest version.

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
anthropics<2.0.65

Exploit evidence

1 public sources

Coverage

News and research mentioning this CVE

Research blogs·research

Timeline

Every event on this vulnerability

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-21852 severity on Zeptric[![CVE-2026-21852](https://zeptric.io/badge/cve/CVE-2026-21852.svg)](https://zeptric.io/cve/CVE-2026-21852)