micro-landing-builder

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts and external CLI tools such as bun and vercel using subprocess.run. These commands are used for project scaffolding, theme validation, and deployment orchestration.
  • [EXTERNAL_DOWNLOADS]: The skill scaffolds projects that depend on well-known packages from the NPM registry, including next, react, radix-ui, and tailwindcss. These dependencies are pinned to specific versions and are standard for the intended application type.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided project metadata, such as slugs, names, and concepts, which are interpolated into the generated application.
  • Ingestion points: Project definitions provided via CLI arguments, CSV files, or JSON files in batch_create.py.
  • Boundary markers: The skill uses a strict regex for slug validation and employs standard JSON serialization when writing project configurations to app.json.
  • Capability inventory: The skill has the capability to write files to the local filesystem and execute subprocesses via subprocess.run.
  • Sanitization: Path traversal is prevented through slug validation and realpath checks in scaffold.py. The generated Next.js application uses React, which provides built-in protection against XSS when rendering user-supplied content.
  • [DYNAMIC_EXECUTION]: The skill uses bun to execute a local TypeScript validator (validate-theme.ts) at runtime to ensure theme configurations meet contrast requirements before scaffolding.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 04:47 PM