auto

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a local Bash script (scripts/auto.sh) to create or remove the .claude/.ref-autotrack marker file based on user input.
  • [COMMAND_EXECUTION]: Embedded shell commands (grep, wc, git) are used to dynamically calculate and display tracking metrics and repository status within the skill's metadata view.
  • [SAFE]: All file system operations and data reads are confined to the local project directory (.claude/ and claude_usage/) for the purpose of managing internal tracking state.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 11:03 PM