Skills
skills/googlechromelabs/web-ai-demos/built-in-ai/Gen Agent Trust Hub

built-in-ai

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The scripts/fetch-idls.js file downloads technical specifications from official webmachinelearning GitHub repositories.
  • Evidence: fetch() calls targeting raw.githubusercontent.com/webmachinelearning/ for Translation, Writing Assistance, and Prompt APIs.
  • Purpose: These downloads are used to update the SKILL.md documentation with the latest Web IDLs.
  • [COMMAND_EXECUTION]: The package.json file contains scripts that execute Node.js commands to manage the skill templates.
  • Evidence: postinstall script runs node scripts/install.js and update-idls runs node scripts/fetch-idls.js.
  • Purpose: These scripts are used to synchronize the skill's instructions into the developer's project root and keep them up to date.
  • [SAFE]: All external resources and code behaviors are consistent with the skill's stated purpose of providing documentation and guidance for Chrome's Built-in AI APIs.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 07:24 PM