zalando-research

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

• Third-party content exposure detected (low risk: 0.10). The agent queries product search, categories, and catalogs from the Zalando marketplace via the Crawlora API, which exposes the LLM to third-party product descriptions and listings.

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 (https://api.crawlora.net/api/v1) using its helper script to fetch search, category, and product data that govern its behavior, but Crawlora is an arbitrary third-party platform lacking strong first-party provenance or independent cryptographic verification, making it a weak/unknown/suspicious dependency.