earn

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly shows publishing and worker workflows that ingest open/public third-party content (e.g., the "Real Examples" Web Scraping with Playwright + Proxy Rotation example and the description template that accepts {"url":"...","selectors":[...]}) and instructs starting a worker to process such incoming tasks, so the agent is expected to fetch and interpret untrusted web/social content as part of its workflow.