Skip to content

CVE-2026-21852 Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation

MediumCVSS 5.3 EPSS 27.5%
Published
Updated
Exploit status
No public exploit known
CISA SSVC
No known exploitation · automatable: yes · technical impact: partial

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.

Upgrade path

3 packages: 2 fixed.

PackageAffectedFixed inStatus
Anthropic claude code < 2.0.65 2.0.65 Fixed
anthropic-ai @anthropic-ai/claude-code(npm) < 2.0.65 2.0.65 Fixed
anthropics claude-code = < 2.0.65 No fix listed Versions listed

Affected products

ProductAffected versionsFixed in
anthropics claude-code = < 2.0.65 No fix listed
anthropic-ai @anthropic-ai/claude-code(npm) < 2.0.65 2.0.65
Anthropic claude code < 2.0.65 2.0.65

References