hm-research

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

• Third-party content exposure detected (low risk: 0.10). The skill fetches H&M product details, reviews, and search results via the Crawlora API, which can contain user-submitted product reviews and outsider-authored content.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill makes runtime API calls to crawlora.net (https://api.crawlora.net/api/v1), which is an arbitrary third-party service and undocumented commercial API provider lacking strong first-party verification.