Kickcall AI Voice Agent — agentic threat model
Kickcall AI Voice Agent presents a high-risk profile due to its integration with sensitive systems like EMRs and CRMs coupled with public voice-channel exposure, making it vulnerable to voice-based prompt injection and unauthorized data access.
OWASP AIVSS score rationale
| Autonomy of Action | 0.70 | |
| Goal-Driven Planning | 0.40 | |
| Self-Modification | 0.00 | |
| Dynamic Tool Use | 0.70 | |
| Persistent Memory | 0.50 | |
| Contextual Awareness | 0.60 | |
| Dynamic Identity | 0.20 | |
| Multi-Agent Interactions | 0.10 | |
| Non-Determinism | 0.60 | |
| Opacity & Reflexivity | 0.70 |
Scored with the canonical OWASP AIVSS formula (AIVSS calculator reference); agentic risk factors estimated from the agent’s described capabilities.
MAESTRO 7-layer threat model
Per-layer threats for this agent. Layers tagged “not certain from listing” are general, caveated commentary where the public description didn’t pin that layer.
Not certain from the listing — The underlying LLMs and STT/TTS models are proprietary or undisclosed. The primary threat is voice-based prompt injection (over-the-air) and adversarial audio inputs designed to bypass system prompts.
The agent utilizes business knowledge bases and integrates with CRMs and EMRs. This introduces severe risks of sensitive data exfiltration (PII/PHI) and knowledge-base poisoning if malicious data is ingested into the RAG pipeline.
The framework orchestrates call routing, calendar bookings, and CRM/EMR updates. Insecure tool integration could allow an attacker to manipulate database records or trigger unauthorized API calls via voice commands.
Not certain from the listing — Details regarding hosting, sandboxing, and network isolation are omitted. The integration with VoIP/UCaaS systems exposes the infrastructure to SIP-based attacks and telephony denial-of-service.
The system features call summaries, intent signals, and sentiment analysis. However, there is a risk of blind spots if these observability tools fail to detect and log adversarial prompt injections or anomalous agent behaviors during live calls.
Not certain from the listing — Despite handling highly regulated healthcare data (EMRs) and customer records (CRMs), the listing does not explicitly cite compliance certifications such as HIPAA, SOC2, or robust access control mechanisms.
Not certain from the listing — While white-label deployment and multi-tenant agency onboarding are supported, there is no explicit mention of multi-agent collaboration or autonomous agent-to-agent marketplaces.
MAESTRO — the 7-layer agentic threat-modeling framework (Cloud Security Alliance / Ken Huang).
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology. Are you the vendor? Factual corrections are free.