Tarota AI — agentic threat model
Tarota AI is a low-risk, entertainment-focused personal assistant for tarot readings with minimal agentic capabilities, presenting primary risks around user data privacy and potential prompt injection.
OWASP AIVSS score rationale
| Autonomy of Action | 0.10 | |
| Goal-Driven Planning | 0.10 | |
| Self-Modification | 0.00 | |
| Dynamic Tool Use | 0.00 | |
| Persistent Memory | 0.20 | |
| Contextual Awareness | 0.20 | |
| Dynamic Identity | 0.00 | |
| Multi-Agent Interactions | 0.00 | |
| Non-Determinism | 0.70 | |
| 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 — likely relies on a third-party commercial LLM prompted for tarot interpretations. Primary threats include prompt injection to bypass the tarot persona or generate inappropriate/harmful life advice.
Not certain from the listing — likely utilizes a static knowledge base of tarot card meanings. Risk of data poisoning is low unless the knowledge base is dynamically updated from unverified external sources.
Not certain from the listing — likely uses a basic conversational chatbot framework. There is no indication of complex tool execution, minimizing the risk of tool misuse or insecure integration.
Not certain from the listing — deployed as a closed-source web application. Standard web application vulnerabilities (e.g., cross-site scripting, insecure session management) represent the primary infrastructure risks.
Not certain from the listing — no guardrails or observability features are mentioned. Lack of input/output filtering could allow the generation of toxic content or misleading psychological advice.
Not certain from the listing — claims to offer 'private' services, but lacks explicit details on data encryption, retention policies, or compliance standards (such as GDPR).
Not certain from the listing — operates as a standalone vertical application with no apparent multi-agent coordination or ecosystem integrations, resulting in negligible ecosystem risk.
MAESTRO — the 7-layer agentic threat-modeling framework (Cloud Security Alliance / Ken Huang).