NYC

vscode-extension-guide

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • COMMAND_EXECUTION (SAFE): The skill provides terminal commands for project setup and management using official tools like yo, npm, and vsce. These are standard for the intended technical use case.
  • EXTERNAL_DOWNLOADS (SAFE): It references the installation of trusted packages from the npm registry, such as @vscode/vsce and @vscode/test-electron, which are necessary for extension development.
  • CREDENTIALS_UNSAFE (SAFE): Guidance regarding Personal Access Tokens (PATs) is consistent with official security practices for publishing to the Marketplace and does not involve hardcoding or unauthorized collection of secrets.
  • PROMPT_INJECTION (SAFE): Prompt templates included for code review tasks are instructional examples and do not contain directives designed to subvert the AI agent's operational boundaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:26 PM