CVE-2026-21852

highpriority · attend · 50EPSS 0.275 · 98 %ileexploit · PoCEUUS

grimoire priorityP1 · Urgent

Exploitable?

Public exploit

4 exploits · PoC

Likely / severe?

27.5% (98th) EPSS

CVSS 7.5 · high

Is it mine?

3 products

Check your exposure

Who says so?

4 sources

cnnvd · enisa_euvd · nvd · osv

EPSS · scored 2026-10-27

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

Technical severity, 0–10. One row per scoring source.

7.5

010

base score 0–10 · higher = more severe · hover a vector to decode⚠ sources disagree · low–high · 2.1–7.5

v3.17.5highCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:Nprimary · NVD / NIST USexploitability 3.9 · impact 3.6

v4.05.3mediumCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:L/SC:N/SI:N/SA:Nsecondary · ENISA EU

v4.05.3mediumCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:Xsecondary · security-advisories@github.com

v4.02.1lowCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:Xsecondary · CVSS-BT (t0sche)

ssvc

A stakeholder decision — act, attend, or track — from exploitation and impact.

Exploitation: none · Automatable: yes · Technical Impact: partialcoordinatorcisa_ssvcUS

weaknesses

The CWE weakness classes this flaw belongs to.

CWE-522USCWE-522US

exploits (4)

Public proof-of-concept and weaponised exploit code.

affected products (3)

Products and version ranges known to be affected.

anthropics claude-code≤ < 2.0.65enisa_euvdEU
anthropic claude code< 2.0.65nvdUScpe:2.3:a:anthropic:claude_code:*:*:*:*:*:*:*:*
npm @anthropic-ai/claude-code< 2.0.65osvUSpkg:npm/%40anthropic-ai/claude-code

advisories (1)

Vendor and ecosystem advisories describing this.

GHSA-jh7p-qr78-84p7Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation2026-01-21ghsa · osvUS
A vulnerability in Claude Code's project-load flow allowed malicious repositories to exfiltrate data including Anthropic API keys before users confirmed trust. If a user started Claude Code in an attacker-controller repository, and the repository included a settings file that set ANTHROPIC_BASE_URL to an attacker-controlled endpoint, Claude Code would issue API requests before showing the trust prompt, including 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 the latest version.

also known as (3)

Other names and identifiers for this entity.

sources

Which sources assert this record, and when.

cnnvd enisa_euvd nvd osv NVD CVE.org MITRE

published 2026-01-21modified 2026-06-17

references (5)

External citations — patches, advisories, analysis.

scry

Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.

Free scan