ecommerce-product-detail

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

• Third-party content exposure detected (high risk: 0.85). The skill navigates to a user-supplied public e-commerce URL (or search results) and then ingests that page’s readable text/JSON-LD/OG/meta into the LLM context via browser-act + eval "$(python scripts/extract-product.py)", which can include outsider-authored free text (e.g., product descriptions/reviews/metadata) from third-party sites.