AirkitAI — agentic threat model
AirkitAI presents a moderate-to-high risk profile due to its autonomous integration with sensitive e-commerce and helpdesk systems, which could allow unauthorized data access or transactional actions if compromised.
OWASP AIVSS score rationale
| Autonomy of Action | 0.80 | |
| Goal-Driven Planning | 0.60 | |
| Self-Modification | 0.10 | |
| Dynamic Tool Use | 0.70 | |
| Persistent Memory | 0.50 | |
| Contextual Awareness | 0.70 | |
| Dynamic Identity | 0.20 | |
| Multi-Agent Interactions | 0.20 | |
| Non-Determinism | 0.50 | |
| 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 — The specific foundation LLMs powering the generative AI features are not disclosed, leaving potential exposure to model-level vulnerabilities like prompt injection or training data leakage unverified.
The platform integrates directly with e-commerce and helpdesk systems, handling sensitive customer PII, order histories, and support tickets. This creates a high-value target for data exfiltration and RAG-based knowledge injection attacks.
AirkitAI uses code-free orchestration to automate routine inquiries and execute actions. Insecure tool integration or prompt injection could lead to unauthorized tool execution, such as modifying orders or triggering fraudulent refunds.
Not certain from the listing — The hosting environment, sandboxing mechanisms for tool execution, and secrets management for e-commerce API keys are not detailed in the public directory listing.
Not certain from the listing — While real-time intelligence gathering is mentioned, the presence of specific guardrails, anomaly detection, or continuous evaluation frameworks is not specified.
Not certain from the listing — Although it is a paid, enterprise-oriented platform, specific compliance alignments (such as SOC2, GDPR, or PCI-DSS for e-commerce) are not explicitly detailed in the listing.
Not certain from the listing — The platform focuses on multi-channel customer support, but there is no explicit mention of multi-agent orchestration, marketplaces, or collaborative agent-to-agent protocols.
MAESTRO — the 7-layer agentic threat-modeling framework (Cloud Security Alliance / Ken Huang).