amazon-one-shot

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md and README explicitly state the agent uses Playwright to navigate and scrape Amazon public pages (e.g., https://www.amazon.com/dp/{ASIN}, /product-reviews/{ASIN}, and /s?k=keyword) and ingests user-generated reviews, listings, and search results which are untrusted third-party content that the agent reads and uses to drive analysis and decisions.