CVE-2026-21852
As of 2026-02-02, CVE-2026-21852 is a CVSS 7.5 (HIGH-severity) vulnerability. EPSS exploitation probability 0.0%. Threadlinqs Intelligence tracks 3 threats exploiting it.
Last updated: 2026-02-02
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
- NVIDIA Releases SkillSpector: Open-Source Security Scanner for AI Agent Skills — LOW
- Internet-Wide Reconnaissance Scans Target MCP Servers and Claude/Cursor AI-Agent Credentials — MEDIUM
- Claude Code RCE & API Key Exfiltration — CVE-2025-59536 + CVE-2026-21852, Untrusted Repo Attack Surface via Hooks, MCP Servers & Environment Variables — HIGH
References
← all vulnerabilities · Markdown version · Threadlinqs Intelligence
Enriched from CVE.org, NVD (this product uses the NVD API but is not endorsed or certified by the NVD), FIRST EPSS, CISA KEV, and GitHub Security Advisories.