swiss-user-research-video-template
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied research data and behavioral findings to generate interactive HTML artifacts.
- Ingestion points: The workflow involves mapping user research tokens (text, percentages, and labels) to variables within
assets/template.html. - Boundary markers: There are no established delimiters or specific instructions for the agent to treat interpolated user data as untrusted.
- Capability inventory: The skill uses
file_writeto generate the primary output and secondary example files. - Sanitization: The skill lacks explicit directives to sanitize or escape user-controlled content before it is injected into the HTML template, which could lead to stored cross-site scripting (XSS) if the generated file is rendered in a browser.
Audit Metadata