amazon-product-research

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md and README explicitly state the agent uses web_fetch and web_search to scrape Amazon product pages (including BSR, prices and user reviews) and Google Trends—public, user-generated/untrusted content—which the agent reads and uses to drive product-analysis decisions, so third‑party content can materially influence its actions.