landing-page-conversion
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation references the use of
npx saglitzdesign-mcp. This command facilitates the download and execution of a Node.js package from a remote registry. This package appears to be a resource provided by the author to extend the skill's functionality.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and improve external marketing copy, which constitutes an attack surface for indirect prompt injection. If the content being audited contains hidden instructions, it could influence the agent's behavior. - Ingestion points: User-provided landing page text, existing marketing copy, and URLs for auditing.
- Boundary markers: No specific delimiters or boundary warnings are provided in the instructions for handling user content.
- Capability inventory: Analyzes copy readability, generates layout systems, and proposes design changes.
- Sanitization: There are no explicit instructions for sanitizing or escaping the content retrieved from landing pages during the audit process.
Audit Metadata