hybrid-scrape-stack

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow explicitly uses Playwright/browser-assisted inspection (step 4) and potentially managed extraction platforms (step 7), which will ingest outsider-authored web page content and network responses (free-form HTML/JSON/text) into the agent’s LLM context via the scraped page/response bodies.