gaming-research

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

• Third-party content exposure detected (medium risk: 0.30). The workflow queries game store APIs like Steam and PlayStation where user reviews, news, and metadata can contain outsider-authored text injected into the agent's context.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill makes runtime HTTP requests to the Crawlora API at https://api.crawlora.net/api/v1 via its helper script, representing an unverifiable external runtime dependency with unknown publisher provenance.