readiness-audit

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow in SKILL.md ingests outsider-authored free text by requesting a user-submitted public storefront URL (step 5) and then scoring/citing “public signals only” from the site’s content (step 6), meaning the agent will read whatever text is present on that submitted URL.