web-scraping-olostep

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 can fetch and ingest arbitrary outsider-authored web page content (e.g., via Create Scrape/Start Crawl/Retrieve Content using user-supplied url_to_scrape/start_url), which is then provided to the agent’s LLM context as readable scraped text—an indirect prompt-injection risk.