onboarding
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill identifies a vulnerability surface where untrusted user input is ingested and written to a persistent file (
SITE.md) without sanitization or boundary markers. - Ingestion points: User responses to business, audience, and brand personality questions are collected via conversation (SKILL.md).
- Boundary markers: Absent. User input is directly interpolated into Markdown templates in the generated
SITE.mdfile. - Capability inventory: The skill utilizes file-writing capabilities to create and maintain
SITE.md. - Sanitization: Absent. There is no escaping or validation of user-provided strings (e.g., business names or taglines) before they are committed to the filesystem.
Audit Metadata