Lakera, a Check Point Subsidiary, Warns of Information Leakage Risk from Claude Code Configuration Files Included in Public Packages
NQ Score
86/100
N1 Content Completeness
90
AI Summary (NQ-processed)
Lakera, a Check Point Software Technologies subsidiary and a global leader in AI-native security platforms for agentic AI applications, has revealed a risk of credential leakage associated with the use of Anthropic's Claude Code. This leakage can occur when configuration files containing credentials, generated during Claude Code's use, are exposed externally upon the publication of npm packages. Lakera's scan identified sensitive information in approximately 1 out of 13 `.claude/settings.local.json` files examined.