lululemon-research

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

• Third-party content exposure detected (medium risk: 0.30). The workflow fetches customer product reviews from an external API (Crawlora API / Lululemon product endpoint), which may contain untrusted user-submitted text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill queries the Crawlora API at runtime via a provided helper script connecting to api.crawlora.net, which is an unknown third-party service provider lacking established first-party provenance or independent cryptographic authentication, presenting a weak external dependency.