scrape

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs using Scrapegraph (e.g., /v1/smartscraper, /v1/markdownify), Olostep (/v1/scrapes, /v1/crawls), Riveter, Brand.dev, and Notte sessions/agents to fetch, crawl, and AI-extract content from arbitrary public URLs, meaning untrusted third-party web content is ingested and can directly influence agent actions.