walmart-research

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

• Third-party content exposure detected (low risk: 0.10). The agent retrieves product listings, descriptions, and user reviews from public Walmart data via the Crawlora API, which can contain outsider-authored text.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill makes runtime calls to the Crawlora API at api.crawlora.net, which is an unknown third-party service provider lacking established first-party provenance, classifying it as a high-risk weak dependency.