medication-information-research

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

• Third-party content exposure detected (low risk: 0.10). The workflow retrieves web content via search and scraping tools (/web/search, /web/scrape), exposing the agent to arbitrary outsider-authored free text from fetched web pages.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill makes runtime API calls to api.crawlora.net which is an unofficial third-party proxy/aggregator service, representing a common unofficial operational dependency.