ljg-classic

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The workflow involves executing local shell commands using the bun runtime to perform rendering (Tools/RenderClassic.ts) and validation (Tools/ValidateClassic.ts) tasks. It also includes initialization commands for installing dependencies and the Playwright browser engine.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the playwright package and its associated Chromium browser binary via bun install and bunx playwright install chromium. These are well-known, trusted tools used for browser automation and rendering.
  • [REMOTE_CODE_EXECUTION]: The skill executes local TypeScript/JavaScript code via bun to process JSON data and generate HTML/PNG artifacts. The rendering logic includes a DOM audit step that evaluates JavaScript within a headless browser context to ensure layout integrity.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it processes ancient Chinese text provided by the user or fetched from the web. The workflow includes boundary checks and round-trip verification to ensure the original text is preserved, and the rendering logic uses HTML escaping to prevent injection within the generated output.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 03:38 AM
Security Audit — agent-trust-hub — ljg-classic