landing-page-generator
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user inputs (Product name, Tagline, Pain points, Benefits) which are interpolated into generated React/Next.js (TSX) and HTML components. A malicious user could provide input containing script tags or other code fragments to compromise the generated application.
- Ingestion points: SKILL.md trigger fields including Product, Tagline, Target audience, Key pain point, and Key benefit.
- Boundary markers: None. There are no instructions for the agent to sanitize or ignore instructions embedded within these fields.
- Capability inventory: The skill generates code files and writes them to the local file system using the agent's file-writing capabilities and the
scripts/landing_page_scaffolder.pyutility. - Sanitization: While the provided Python script escapes data for HTML output, the TSX generation path uses direct string interpolation for various fields (e.g., features, pricing plans) without sanitization.
- [DYNAMIC_EXECUTION]: The skill includes a Python utility,
scripts/landing_page_scaffolder.py, designed to scaffold and generate production-ready code files at runtime. The script assembles TSX and HTML through template-based string concatenation, which is a form of dynamic code generation based on user-influenced configuration files.
Audit Metadata