Webex AI Agents — agentic threat model
Webex AI Agents present a moderate-to-high risk profile due to their integration into enterprise contact centers and CRM systems, combined with the capability for users to build custom agents via AI Agent Studio, which requires robust guardrails to prevent data exfiltration and prompt injection.
OWASP AIVSS score rationale
| Autonomy of Action | 0.70 | |
| Goal-Driven Planning | 0.50 | |
| Self-Modification | 0.20 | |
| Dynamic Tool Use | 0.60 | |
| Persistent Memory | 0.50 | |
| Contextual Awareness | 0.70 | |
| Dynamic Identity | 0.40 | |
| Multi-Agent Interactions | 0.60 | |
| Non-Determinism | 0.60 | |
| 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 — Webex AI Agents likely use proprietary or third-party LLMs integrated into Cisco's ecosystem. Threats include prompt injection, adversarial inputs, and misaligned outputs in customer-facing chat.
Not certain from the listing — Likely integrates with Webex Contact Center databases and customer CRM data. Risks include data exfiltration, unauthorized access to customer records, and training/RAG data poisoning.
The AI Agent Studio allows custom agent creation and deployment. Orchestration risks include insecure tool integration, prompt injection leading to unauthorized tool execution, and memory poisoning within customer sessions.
Not certain from the listing — Hosted within Cisco's enterprise cloud infrastructure. Threats include container escape, API exposure, and unauthorized access to the AI Agent Studio management console.
Not certain from the listing — Enterprise-grade logging is expected from Cisco, but specific AI guardrails or drift detection mechanisms are not detailed. Risks include blind spots in conversational anomalies.
As a Cisco product, it inherits enterprise-grade compliance (SOC2, ISO, GDPR alignment). However, custom agents built via AI Agent Studio must be governed to prevent compliance drift and data privacy violations.
The AI Agent Studio supports deploying multiple custom agents. Risks include cascading failures, unauthorized agent-to-agent communication, and trust abuse between custom-built enterprise agents.
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.