personal-tool-builder

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE] (SAFE): Code examples utilize homedir() to create a hidden configuration directory (.mytool) for storing local JSON or SQLite data. This is standard practice for local-first applications and does not attempt to access sensitive system files like credentials or SSH keys.
  • [COMMAND_EXECUTION] (SAFE): The skill provides templates for CLI tools using commander (Node.js) and click (Python). These are industry-standard libraries for argument parsing. No suspicious or arbitrary shell command execution patterns were found.
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill documentation lists standard dependencies in a package.json template (e.g., chalk, ora, inquirer, conf). These are trusted, widely-used packages for CLI development. There are no automated installation scripts or remote code downloads.
  • [PROMPT_INJECTION] (SAFE): The content consists of instructional methodology and code snippets for tool building. No attempts to override agent behavior or bypass safety filters were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:38 PM