oldnavy-research

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

• Third-party content exposure detected (low risk: 0.10). The skill fetches product catalogs and customer reviews from the Crawlora API, where customer reviews contain outsider-authored text ingested at runtime.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill relies on an external API service hosted at crawlora.net via curl execution in its helper script, representing an unknown third-party operational dependency.