app-store-api

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

• Third-party content exposure detected (low risk: 0.10). The agent reads public app store listings, descriptions, and user reviews from the Apple App Store via the ReplyNodes API, which can contain user-submitted untrusted text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill documentation includes an installation command fetching from a GitHub repository (https://github.com/replynodes/replynodes-agent-skills), which constitutes an operational dependency with common unofficial or third-party provenance.