where-to-start
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from user messages and external websites (homepage, pricing, marketplace pages) via the host's web fetch or browser tools.
- Ingestion points: Data enters the context through user input and external website content fetched during Step 1 ('Look before asking').
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing fetched web content.
- Capability inventory: The skill uses
gooseworks:file_writeto modify thebrand/situation.mdworkspace file andgooseworks:brand_updateto update brand onboarding profiles. - Sanitization: There are no explicit instructions for sanitizing or escaping content before it is used to update internal records, although a human-in-the-loop confirmation (Step 6) is required before saving final recommendations.
Audit Metadata