extract-webpage-data

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 the agent to scrape and ingest arbitrary public web pages (e.g., "orth run scrapegraph /v1/smartscraper -d {'website_url':'https://example.com/team','user_prompt':...}" and Olostep/Riveter scrape endpoints), meaning untrusted third‑party page content is read and used by the AI to produce actions/answers and could therefore carry indirect prompt-injection instructions.