vobiz-voice-calls

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

• Third-party content exposure detected (high risk: 0.70). The required workflow is to call Vobiz APIs and (critically) to POST to a user-supplied answer_url that returns VobizXML; that returned free-form text is read by the agent at runtime, and since it comes from an external endpoint not authored by the operating user, it is outsider-authored content that can contain prompt-injection payloads.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires a runtime "answer_url" HTTPS endpoint (answer_url) that Vobiz will POST to and which must return VobizXML that directly controls call behavior and prompts, so an external URL provided at runtime controls the agent flow.