blog-generation

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md’s required runtime workflow reads and ingests the brand’s site content via firecrawl_urls_scrape / web_scrape_page (public web content fetched at runtime), which can include outsider-authored free text and prompt-injection payloads that then enter the agent’s LLM context.