ecommerce-listing

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

• Third-party content exposure detected (high risk: 0.85). The skill navigates to runtime-constructed e-commerce search/category URLs and then runs extract-listing.py, which reads outsider-authored free text from the fetched page DOM/JSON-LD (e.g., product names/prices/ratings from third-party sites) into the agent’s LLM context via the tool’s JSON output.