sinch-voice-api

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow for this skill is handling Sinch Voice callback events (ICE/ACE/PIE) where the agent must read outsider-authored JSON fields like menuResult.value / cli from the inbound POST body and use them to generate SVAML responses, which then become LLM context (indirect prompt injection risk via untrusted callback payload text).