Claude Code is an agentic coding tool. Prior to version 2.0.65, vulnerability in Claude Codes 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 users 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.
Weakness
The product transmits or stores authentication credentials, but it uses an insecure method that is susceptible to unauthorized interception and/or retrieval.
Affected Software
| Name | Vendor | Start Version | End Version |
|---|---|---|---|
| Claude_code | Anthropic | * | 2.0.65 (excluding) |
Potential Mitigations
Related Attack Patterns
- https://cwe.mitre.org/data/definitions/102.html
- https://cwe.mitre.org/data/definitions/474.html
- https://cwe.mitre.org/data/definitions/50.html
- https://cwe.mitre.org/data/definitions/509.html
- https://cwe.mitre.org/data/definitions/551.html
- https://cwe.mitre.org/data/definitions/555.html
- https://cwe.mitre.org/data/definitions/560.html
- https://cwe.mitre.org/data/definitions/561.html
- https://cwe.mitre.org/data/definitions/600.html
- https://cwe.mitre.org/data/definitions/644.html
- https://cwe.mitre.org/data/definitions/645.html
- https://cwe.mitre.org/data/definitions/652.html
- https://cwe.mitre.org/data/definitions/653.html