engineering-advanced-skills

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly includes a browser-automation capability that instructs the agent to scrape and extract data from arbitrary public websites and to drive actions based on page content (see browser-automation/SKILL.md "Use when ... scraping sites" and the scraping workflows that read page content, follow pagination and fill forms), which means untrusted third‑party content is fetched and interpreted as part of the agent's workflow and could materially influence subsequent actions.