tooling-init
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill uses
npm install,pnpm add,yarn add, andbun addto install developer dependencies from the official npm registry. - [REMOTE_CODE_EXECUTION]: The skill executes
npm init playwright@latest(and manager-specific equivalents), which downloads and runs a trusted initialization script provided by the Playwright project. - [COMMAND_EXECUTION]: The skill performs shell commands to verify the project setup, specifically
npm run formatandnpm run check, which execute the locally configured toolchain. - [DATA_EXPOSURE]: The skill reads local project configuration files, including
package.json,tsconfig.json, and existing tool configs, to identify the project structure and prevent clobbering existing settings. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted metadata from the project environment.
- Ingestion points:
package.json, lockfiles, and existing.prettierrcoreslint.configfiles. - Boundary markers: The skill does not explicitly use boundary markers when reading file content, but it limits its evaluation to structural properties (e.g., checking for existence or specific keys).
- Capability inventory: The skill has access to shell execution (
npm), package installation, and file writing. - Sanitization: No explicit sanitization of input data is described, but usage is limited to standard configuration parameters.
Audit Metadata