AgentReadyHomeAgent Listing

← TarotRead AI

TarotRead AI — agentic threat model

4.0AIVSS 4.0 · Medium

TarotRead AI is a low-risk entertainment agent with minimal agentic capabilities, posing negligible threat to external systems due to its lack of tool integration, planning, or autonomous execution capabilities.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 2.5AARS uplift 1.49Factor sum 2.2/10Threat ×0.9Mitigation ×1.0
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
0.30
Dynamic Identity
0.00
Multi-Agent Interactions
0.00
Non-Determinism
0.80
Opacity & Reflexivity
0.70

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.

L1 · Foundation Models⚠ not certain from listing

Not certain from the listing — likely utilizes a third-party commercial foundation model customized via system prompting. Primary threats are prompt injection leading to offensive outputs or jailbreaks, and model alignment issues.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — may use a basic knowledge base or vector store for tarot card meanings and interpretations. Risk of data poisoning is low but could result in corrupted or nonsensical readings.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — likely uses a simple API wrapper rather than a complex agentic framework. There are no apparent tools or complex orchestration mechanisms to exploit.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — hosted as a standard web application. Standard web infrastructure threats apply, such as unauthorized access to user accounts or exposure of personal dream/relationship logs.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — likely lacks advanced LLM observability or real-time guardrails, relying instead on basic input filtering and static system prompts.

L6 · Security & Compliance (cross-cutting)⚠ not certain from listing

Not certain from the listing — as a freemium entertainment application, it is unlikely to implement rigorous enterprise security controls, SOC2 compliance, or strict data privacy audits.

L7 · Agent Ecosystem✓ mapped

The agent operates entirely as a standalone consumer application with no multi-agent collaboration, marketplace integrations, or external agent-to-agent communication channels.

MAESTRO — the 7-layer agentic threat-modeling framework (Cloud Security Alliance / Ken Huang).