Teneo.ai — agentic threat model
Teneo.ai is an enterprise-grade voice automation and customer service platform; its primary risks stem from handling sensitive customer PII and integration with telephony/CRM systems, which could be targeted for data exfiltration or social engineering.
OWASP AIVSS score rationale
| Autonomy of Action | 0.70 | |
| Goal-Driven Planning | 0.50 | |
| Self-Modification | 0.10 | |
| Dynamic Tool Use | 0.60 | |
| Persistent Memory | 0.50 | |
| Contextual Awareness | 0.70 | |
| Dynamic Identity | 0.20 | |
| Multi-Agent Interactions | 0.30 | |
| Non-Determinism | 0.40 | |
| Opacity & Reflexivity | 0.50 |
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 — Teneo is a platform that can integrate various NLU and LLM engines, making it susceptible to model-specific threats like prompt injection or adversarial inputs depending on the chosen foundation model.
Not certain from the listing — The platform processes voice transcripts and customer data, which presents risks of data exfiltration or unauthorized access to backend knowledge bases, though specific vector store implementations are not detailed.
Not certain from the listing — Teneo uses its own proprietary conversational AI framework for dialogue management. Insecure tool integration with CRMs or external APIs could lead to unauthorized actions if the orchestration layer is compromised.
Not certain from the listing — As a closed-source enterprise platform, it is likely hosted in secure cloud environments, but specific sandboxing, containerization, or network isolation details are not provided.
Not certain from the listing — Teneo typically includes analytics and session monitoring, but the listing does not specify the presence of real-time guardrails or automated drift detection mechanisms.
Not certain from the listing — While enterprise customer service platforms generally adhere to strict compliance standards (like GDPR or SOC2), the brief listing does not explicitly detail its security controls or compliance certifications.
Not certain from the listing — The platform primarily focuses on single-agent voice automation and customer service, but integration with telephony networks (IVR) and external APIs introduces potential cascading failure risks.
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.