create-an-asset

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 1 "Always Research" and earlier steps explicitly instruct the agent to search and extract data from public third-party sources (e.g., company websites, LinkedIn, Crunchbase, investor presentations) and to "extract" brand colors and leadership quotes, meaning the agent will ingest untrusted public web content that can influence asset generation and subsequent actions.