The package has no npm install hook and the tracking behavior is activated by the user’s assessment setup command, with its scope disclosed in the command output. Because it modifies AI tool configuration and captures prompt text, the explicit-command agent capability warrants a warning, but source inspection did not establish a malicious chain.
Static reason
No blocking static signals were detected.; previous stored version diff introduced dangerous source
Trigger
The user runs `litmus init <token>` for an assessment.
Impact
Assessment prompts from the configured folder are recorded and sent to the assessment backend; the hooks also alter AI tool configuration.
Mechanism
Setup writes hook configuration for supported AI tools. The hook logger captures prompt text in the assessment folder and posts activity events to the backend URL and activity path configured for the assessment.
Evidence
dist/commands/init.jsdist/lib/ai-tracking.jsdist/lib/hook-logger.cjs