online-shopping

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

• Third-party content exposure detected (low risk: 0.10). The skill uses DeepAPI to search the web, scrape websites, and read social media feeds, which involve actively fetching and consuming external search results, scraped web pages, and user reviews from selected or searched sources.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to query external search and scraping endpoints at https://deepapi.co as an operational instruction source for shopping research, representing a weak/unknown third-party service dependency.