squeeze-page-builder
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill accepts several free-text inputs from the user (such as
lead_magnet.title,affiliate_product.url, andtarget_audience) and interpolates them directly into a generated HTML file. The resulting file includes JavaScript that uses these inputs (e.g., for redirects). There are no instructions for sanitizing or escaping these inputs to prevent code injection in the generated output. - Ingestion points: Input schema variables defined in
SKILL.mdsuch aslead_magnetandaffiliate_product. - Boundary markers: Absent; the skill does not use delimiters or instructions to ignore embedded commands in the user-provided data.
- Capability inventory: The skill generates executable HTML and JavaScript files meant to be saved and deployed by the user.
- Sanitization: Absent; there is no mention of HTML escaping or URL validation for the generated code.
Audit Metadata