dbcve.org
Claude CodeApplication · Anthropic

CVE-2026-21852

HIGH · 7.5 CVSS v3.1 Published 2026-01-21
Fix available
A fix is available. Upgrade to 2.0.65 or later.
See remediation →
84/100
Remediation priority · High
Remotely reachable No privileges Zero-click

Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.

NVD · unedited
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.

Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.

dbcve analysis · moderate confidence

In Claude Code prior to version 2.0.65, a vulnerability in the project-load flow allowed malicious repositories to exfiltrate user data including Anthropic API keys. Attackers could embed a settings file that configures ANTHROPIC_BASE_URL to an attacker-controlled endpoint; when users opened the repository, Claude Code would read this configuration and immediately issue API requests before displaying the trust confirmation prompt, thereby leaking credentials to the attacker.

MitigationUpdate Claude Code to version 2.0.65 or later. The patch ensures the trust prompt appears before any configuration from untrusted repositories is read or used for API requests.

Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.

Affected products & versions What the vendor confirmedThe version ranges the vendor confirmed as vulnerable. If your version sits inside a range here, treat yourself as exposed until you have upgraded.

NVD · CPE data
Claude CodeApplication
Affected:< 2.0.65

CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.

From the vector
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
None
Availability
None

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

Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.

dbcve checks

Work through these to decide whether this CVE applies to you.

  1. Check installed Claude Code version
    Run 'claude --version' or check the application bundle/version info to determine the exact version number
    Affected if The version is lower than 2.0.65 (e.g., 2.0.64, 2.0.60, etc.)
  2. Identify custom ANTHROPIC_BASE_URL configuration
    Check environment variables and Claude Code configuration files for any ANTHROPIC_BASE_URL setting pointing to an untrusted or non-Anthropic endpoint
    Affected if ANTHROPIC_BASE_URL is set to a domain you do not control or recognize
  3. Inspect repository settings files
    Review any .claude/settings.json or similar configuration files from recently opened repositories for unexpected API endpoint configurations
    Affected if A repository contains a settings file that defines a custom base URL for API requests
  4. Review network connections
    Monitor outgoing HTTPS connections from Claude Code during repository opening to identify requests to unexpected domains
    Affected if API requests are being sent to non-Anthropic domains before any trust confirmation prompt appears

You are affected if Claude Code version is below 2.0.65 AND you have opened or trust any repository containing a custom ANTHROPIC_BASE_URL configuration.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.

dbcve · scoped
Upgrade available Upgrade to 2.0.65 or later
Fixed in 2.0.65
Interim mitigation

Update Claude Code to version 2.0.65 or later. The patch ensures the trust prompt appears before any configuration from untrusted repositories is read or used for API requests.

Recommended fix High confidence

2.0.65 (or latest available version)

  1. Check the currently installed Claude Code version (typically via the Claude Code CLI or application about/settings

Generated from the published advisory — verify against the referenced sources before acting.

Fix this in Claude Code Scoped from the published advisory
  • Consultation1.0 h
  • Implementation1.0 h
  • Testing2.0 h
  • Review / QA1.0 h
5.0 hours of engineering $860
Get the upgrade done

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $1,376.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-21852 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

Get it on GitHub Scan in the browser

References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.

Primary sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2026-21852 in production — separate from our analysis above.

No notes yet

Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.

What this is

A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.

What belongs here
  • Verified mitigations, workarounds, and config changes
  • Version or environment caveats, and links to real fixes
  • No weaponised exploit code, or anything meant to cause harm
  • No spam, self-promotion, credentials, or personal data