amazon-store-research

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly navigates to and scrapes arbitrary, user-provided Amazon Stores pages (see Step 1.2: mcp__playwright__browser_navigate and browser_evaluate extracting DOM from the store URL) and then feeds that scraped, third‑party content into multiple analysis agents whose outputs drive decisions and reports, thereby exposing the agent to untrusted third‑party content that could carry indirect prompt-injection.