seo-analyzer

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

• Third-party content exposure detected (high risk: 0.85). The workflow uses runtime web crawling/scraping via outsider-controlled sources (e.g., curl .../v1/proxy/orthogonal/run with api:"tavily" and api:"scrapegraph" to fetch arbitrary url/page content), which is then ingested as readable page text into the agent’s LLM context for analysis.