vscode

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill describes using the Visual Studio Code CLI to install extensions from the official marketplace. Evidence: The command code --install-extension esbenp.prettier-vscode is provided as an example for managing editor extensions.
  • [COMMAND_EXECUTION]: The skill leverages standard development tools and CLI utilities to automate workspace workflows. Evidence: Instructions include the use of the code CLI (code ., code --diff) and npm scripts within VS Code tasks (npm test, npm run lint).
  • [INDIRECT_PROMPT_INJECTION]: The skill manages VS Code workspace configuration files (.vscode/tasks.json, .vscode/launch.json) which could contain untrusted instructions if modified by external parties in a shared environment. 1. Ingestion points: Project configuration files located in the .vscode/ directory. 2. Boundary markers: The skill incorporates a security best practice by advising the agent to prefer "workspace Trust awareness" when recommending or running tasks that involve shell execution. 3. Capability inventory: The skill enables automation via shell command execution (tasks) and the code command-line interface. 4. Sanitization: The workflow relies on the editor's built-in security features (Workspace Trust) to validate the safety of project-specific configurations.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 04:39 AM