company-intel

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

• Third-party content exposure detected (high risk: 0.85). The workflow calls runtime endpoints like /v1/brand/retrieve (brand-dev), /v1/people-search (fiber), and /v1/smartscraper (scrapegraph) that can fetch/scrape third-party web/company text and pass it back into the agent’s LLM context as free-form content (classic public-web/outsider-authored text ingestion via scraping/search APIs).