What is CVE-2026-21852?
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.
The record classifies CVE-2026-21852 under weakness class CWE-522. Its CVSS v3 base vector states that the flaw is reachable remotely over the network, needs no prior authentication, needs no user interaction, and has high impact on confidentiality. 1 affected-product entry is recorded, across 1 vendor, listed below. The identifier was first published 280 days ago.
Severity and exploitation probability
- CVSS v3.1 base score
- 7.5 — HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N - CVSS v4.0 base score
- 5.3
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N - EPSS (FIRST)
- 27.8% probability of exploitation in the next 30 days, higher than 98.0% of all scored CVEs
- CISA KEV
- Not listed in the CISA Known Exploited Vulnerabilities catalog
- Threadlinqs priority
- 9.7/10 — a Threadlinqs composite of the CVSS base score, the EPSS percentile and public exploit availability
- Published
- 2026-01-21
Is CVE-2026-21852 being exploited?
Weaponised exploit code for CVE-2026-21852 is publicly available. 4 public proof-of-concept repositories are tracked for this identifier. It currently carries a trending score of 38 in the Threadlinqs vulnerability feed.
- atiilla/CVE-2026-21852-PoC (github)
- TreRB/ai-ide-config-guard (github)
- Perufitlife/dotclaude-security (github)
- abhishek2512mishra/claude-code-security-audit (github)
Affected products and versions
- Anthropic: Claude Code
How to fix CVE-2026-21852
The record marks a vendor fix as available for CVE-2026-21852. Patch reference: https://github.com/anthropics/claude-code/security/advisories/GHSA-jh7p-qr78-84p7. Vendor advisory: https://github.com/anthropics/claude-code/security/advisories/GHSA-jh7p-qr78-84p7. Apply the vendor fix referenced above to every affected product listed in this record, then confirm the running version against the vendor advisory.
Threat activity tracking CVE-2026-21852
3 tracked threats in the Threadlinqs corpus reference CVE-2026-21852, either in the campaign’s CVE list or as an indicator on the campaign record.
- NVIDIA Releases SkillSpector: Open-Source Security Scanner for AI Agent Skills — LOW · 2026-08-03
- Internet-Wide Reconnaissance Scans Target MCP Servers and Claude/Cursor AI-Agent Credentials — MEDIUM · 2026-07-13
- Claude Code RCE & API Key Exfiltration — CVE-2025-59536 + CVE-2026-21852, Untrusted Repo Attack Surface via Hooks, MCP Servers & Environment Variables — HIGH · 2026-02-26
Sources
Enriched from CVE.org, FIRST EPSS, public proof-of-concept repositories. Last verified by Threadlinqs on .