Claude Code is an agentic coding tool. Versions before 1.0.111 were vulnerable to Code Injection due to a bug in the startup trust dialog implementation. Claude Code could be tricked to execute code contained in a project before the user accepted the startup trust dialog.
Exploiting this requires a user to start Claude Code in an untrusted directory. Users on standard Claude Code auto-update will have received this fix automatically. Users performing manual updates are advised to update to the latest version.
This issue is fixed in version 1.0.111.
Attack Parameters
Attack Vector
Network
Атака возможна удалённо
Attack Complexity
Low
Легко эксплуатировать
Attack Requirements
None
Нет дополнительных условий
Privileges Required
None
Права не нужны
User Interaction
Passive
Минимальное взаимодействие
Impact Assessment
Confidentiality
High
Полная утечка данных
Integrity
High
Полная модификация данных
Availability
High
Полный отказ в обслуживании
CVSS Vector v4.0
Weakness Type (CWE)
Vulnerable Products 1
anthropic:claude_code
Known Affected Software Configurations 1
| Configuration | From (including) | Up to (excluding) |
|---|---|---|
|
Anthropic Claude_Code
cpe:2.3:a:anthropic:claude_code:*:*:*:*:*:node.js:*:*
|
— |
1.0.111
|