AgentReadyHomeAgent Listing

← Entobase AI

Entobase AI — agentic threat model

8.9AIVSS 8.9 · High

Entobase AI acts as a high-value financial intermediary matching users with over 100 lenders, presenting significant systemic risk due to the handling of sensitive PII and financial data across embedded third-party environments without disclosed security controls.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 8.5AARS uplift 0.39Factor sum 2.5/10Threat ×1.05Mitigation ×1.0
Autonomy of Action
0.30
Goal-Driven Planning
0.20
Self-Modification
0.00
Dynamic Tool Use
0.40
Persistent Memory
0.20
Contextual Awareness
0.50
Dynamic Identity
0.00
Multi-Agent Interactions
0.00
Non-Determinism
0.30
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.

L1 · Foundation Models⚠ not certain from listing

Not certain from the listing — likely uses proprietary algorithms or LLMs to analyze financing needs. Threats include prompt injection to manipulate loan eligibility criteria or model stealing of the proprietary matching logic.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — processes highly sensitive financial PII and credit application data. Threats include data exfiltration of user applications, unauthorized access to credit profiles, and lack of secure data lineage.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — orchestrates data flow to match users with 100+ lenders. Threats include insecure API integrations, parameter tampering in loan applications, and tool misuse during lender querying.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — deployed as a web application and an embedded widget for third-party businesses. Threats include widget-based cross-site scripting (XSS), API key exposure, and host website compromise.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — requires rigorous monitoring to prevent algorithmic bias in loan matching and to detect drift in lender API responses. Threats include blind spots in automated decision-making.

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

Not certain from the listing — operates in a highly regulated FinTech space requiring compliance with KYC, AML, and data protection laws. Threats include regulatory non-compliance and lack of robust audit trails for loan matching.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — interacts with a vast ecosystem of 100+ external lender APIs and embedded merchant sites. Threats include cascading failures from compromised lender endpoints and trust abuse between host sites and the embedded widget.

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