skillify

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

• Third-party content exposure detected (high risk: 0.85). The required workflow includes a runtime browser-scrape step ($B goto "<TARGET_URL>" then $B html > ...), where the fetched page content is outsider-authored public web text that becomes LLM-readable prose via the staged fixtures/...html and is later parsed by script.ts/tests.