product-spec-bulk-fetch

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md "Fetch the page" step and the included "WebFetch Extraction Prompt") instructs the agent to fetch and parse arbitrary product pages from user-provided/public URLs and use the extracted fields to drive actions (populate the master Google Sheet and categorize/save products), meaning untrusted third‑party web content is read and can materially influence tool use and decisions.