setup
Warn
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: MEDIUMCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill modifies the
~/.claude/settings.jsonfile to inject a complex multi-line shell script into thestatusLineconfiguration. This script is designed to run automatically in the background, using tools likels,uv,jq, andmcplto gather and display environment metadata. - [COMMAND_EXECUTION]: Executes several shell commands for system preparation, including
catto read existing configurations,mkdirto create rules directories, andcp -rto copy template files from the plugin root to the user's home directory. - [COMMAND_EXECUTION]: Utilizes a Python one-liner (
python3 -c) to programmatically parse and check for duplicate notification hooks within the user's settings file. - [COMMAND_EXECUTION]: Invokes a local Python script bundled with the skill (
sync_context.py) usinguv runto generate and update the assistant's core rule files.
Audit Metadata