Threat Intelligence / CVE / CVE-2026-21852

CVE-2026-21852

CVSS 7.5 (HIGH) · EPSS 0.0% · Published 2026-01-21

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.

CVSS v3 vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

Weaknesses (CWE)

CWE-522

Threats tracking this CVE

Claude Code RCE & API Key Exfiltration — CVE-2025-59536 + CVE-2026-21852, Untrusted Repo Attack Surface via Hooks, MCP Servers & Environment Variables — HIGH

References

https://github.com/anthropics/claude-code/security/advisories/GHSA-jh7p-qr78-84p7

Full detection coverage & IOCs for threats exploiting CVE-2026-21852 are available via the Threadlinqs MCP server (Purple tier). View plans →

Markdown version · Threadlinqs Intelligence