programmatic-seo

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "Data Acquisition & Enrichment" and "Data sources by type" sections explicitly instruct scraping public websites and ingesting user-generated content (reviews, ratings, photos) and public databases/APIs as part of the pipeline, which the agent is expected to read and use to generate pages — creating a clear vector for untrusted third-party content to influence actions.