product-feed-optimizer

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md’s runtime workflow ingests the user-author provided product-feed export/diagnostics and scraped destination landing-page content as untrusted input (“Reads”) and then LLM-processes fields like titles/descriptions/price/availability, so outsider-written free text can be supplied via the feed/landing pages the workflow consumes.