CVE-2026-21852
Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation
CVE-2026-21852 is a medium vulnerability (CVSS 5.3) in Anthropic Claude Code, published January 21, 2026. Public exploit code exists. EPSS puts the chance of exploitation in the next 30 days at 27.5%, the 98th percentile. Fixed in @anthropic-ai/claude-code 2.0.65.
- Severity
- 5.3 MediumCVSS 4.0, CVE List
- Exploit chance
- 27.5%EPSS, 98th percentile
- Exploitation
- None known4 public exploits
- Fixed in
2.0.65@anthropic-ai/claude-code
Description
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.
Attack profile
How easy it is to exploit
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- None
- User interaction
- Passive
What an attacker can affect
- Confidentiality
- Low
- Integrity
- Low
- Availability
- Low
Exploit likelihood
Discussion
Affected products
Affected packages
| Package | Affected | Fixed |
|---|---|---|
@anthropic-ai/claude-codenpm | before 2.0.65 | 2.0.65 |
Public exploits
Links only. Every CVE stores no exploit code.
| Source | Link | Date |
|---|---|---|
| PoC in GitHub | Perufitlife/dotclaude-security | 2026-06-21 |
| PoC in GitHub | TreRB/ai-ide-config-guard | 2026-04-20 |
| PoC in GitHub | abhishek2512mishra/claude-code-security-audit | 2026-09-13 |
| PoC in GitHub | atiilla/CVE-2026-21852-PoC | 2026-02-27 |
What each source reports
CVE List Score used
Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation
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.
- Record
CVE-2026-21852- CVSS 4.0
- 5.3 Medium
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 - Weakness
- CWE-522
- Updated
- 2026-11-02
EUVDEUVD-2026-3597
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.
- Record
EUVD-2026-3597- CVSS 4.0
- 5.3 Medium
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 - Updated
- 2026-11-02
GitHub AdvisoriesGHSA-jh7p-qr78-84p7
Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation
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.
- Record
GHSA-jh7p-qr78-84p7- CVSS 4.0
- 5.3 Medium
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 - Weakness
- CWE-522
- Updated
- 2026-11-02
NVD
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.
- Record
CVE-2026-21852- CVSS 4.0
- 5.3 Medium
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/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:X - CVSS 3.1
- 7.5 High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N - Weakness
- CWE-522
- Updated
- 2026-11-02
OSVGHSA-jh7p-qr78-84p7
Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation
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.
- Record
GHSA-jh7p-qr78-84p7- CVSS 4.0
- 5.3 Medium
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 - Weakness
- CWE-522
- Updated
- 2026-11-02
History
| Recorded | Changed | Sources |
|---|---|---|
| first indexed | CVE List, EUVD, GitHub Advisories, NVD, OSV, PoC in GitHub |
Dates are when Every CVE recorded each change. Upstream dates may differ.