get-brand-assets

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.65). The skill calls the Brand.dev API via the user-supplied domain (e.g., stripe.com) through $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run, and that runtime extraction can include free-form text scraped from third-party company websites, which the LLM may ingest as readable content—an outsider source.