@saluzi/saluzi-edu@0.7.2
Saluzi CLI - interactive AI coding assistant in the terminal
AI security review
scanned · by lpm-firewall-aiThe postinstall hook automatically writes permission settings for the package's own AI assistant outside the package directory, creating an agent configuration lifecycle risk. The change only adds protective deny rules and preserves existing settings, so the evidence does not support blocking publication as malicious.