webinar-registration-page
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted user data and interpolates it into generated HTML and JavaScript code without explicit sanitization instructions.\n
- Ingestion points: The
SKILL.mdfile defines an input schema that accepts user-provided text for event titles, presenter biographies, and affiliate product descriptions.\n - Boundary markers: There are no instructions or delimiters designed to separate user-provided data from the generated code structure.\n
- Capability inventory: The skill generates functional JavaScript for countdown timers and form redirects (using
window.location.href), which could be manipulated if input is not properly handled.\n - Sanitization: The workflow lacks explicit steps for sanitizing or escaping user input before it is placed into the code blocks.
Audit Metadata