Reiki — agentic threat model
Reiki is an AI agent creation and monetization platform combining Web3 and AI; its primary risk lies in its marketplace ecosystem and the potential for deploying insecure or malicious user-generated agents with financial or on-chain capabilities.
OWASP AIVSS score rationale
| Autonomy of Action | 0.50 | |
| Goal-Driven Planning | 0.40 | |
| Self-Modification | 0.20 | |
| Dynamic Tool Use | 0.60 | |
| Persistent Memory | 0.40 | |
| Contextual Awareness | 0.50 | |
| Dynamic Identity | 0.60 | |
| Multi-Agent Interactions | 0.50 | |
| Non-Determinism | 0.70 | |
| Opacity & Reflexivity | 0.60 |
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 models used by Reiki's built agents are not disclosed, leaving risks like model alignment, adversarial vulnerability, and data poisoning unquantified.
Not certain from the listing — Details regarding data ingestion, RAG capabilities, vector database hosting, and privacy controls for user-created agents are not specified.
Reiki provides a drag-and-drop interface with pre-built components and templates. This introduces risks of insecure default configurations, template injection, and flawed orchestration logic if the pre-built blocks lack rigorous input validation.
Not certain from the listing — The hosting environment, execution sandboxing for deployed agents, and secret management for third-party integrations are not detailed.
Not certain from the listing — It is unclear what monitoring, logging, or guardrail mechanisms are provided to creators or platform administrators to detect anomalous agent behavior.
The platform utilizes blockchain-based on-chain ownership proof to secure intellectual property and manage monetization. However, traditional access control, authentication, and regulatory compliance frameworks are not detailed.
As a multi-agent monetization platform and marketplace, Reiki faces significant ecosystem risks, including the distribution of malicious/compromised agents, financial fraud via monetization channels, and cascading failures in multi-agent integrations.
MAESTRO — the 7-layer agentic threat-modeling framework (Cloud Security Alliance / Ken Huang).