AgentReadyHomeAgent Listing

← HAPAX

HAPAX — agentic threat model

7.3AIVSS 7.3 · High

Hapax presents low agentic execution risk due to its primary role as an informational chat and knowledge retrieval assistant, but it carries extremely high data security and confidentiality risks due to its reliance on a massive, proprietary dataset of sensitive banking conversations and documents.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 7.5AARS uplift 0.57Factor sum 2.3/10Threat ×1.0Mitigation ×0.9
Autonomy of Action
0.20
Goal-Driven Planning
0.20
Self-Modification
0.00
Dynamic Tool Use
0.20
Persistent Memory
0.20
Contextual Awareness
0.60
Dynamic Identity
0.00
Multi-Agent Interactions
0.00
Non-Determinism
0.40
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.

L1 · Foundation Models✓ mapped

Utilizes a 'Proprietary Banking LLM'. The primary threats at this layer are model stealing (due to the high value of a domain-specific financial model) and membership inference attacks that could expose proprietary training data.

L2 · Data Operations✓ mapped

Relies on a massive proprietary dataset (20,000+ documents, 10,000+ hours of videos, and 230,000+ banker conversations). This makes it highly vulnerable to data exfiltration, embedding inversion, and knowledge-base poisoning if malicious data is ingested into the CBANC pipeline.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — the orchestration framework is not specified, but threats would include prompt injection bypassing the chat assistant's guardrails to access unauthorized documents within the Knowledge Hub.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — deployment details are proprietary, but hosting in a secure, isolated tenant per institution is critical to prevent cross-tenant data leakage of sensitive banking data.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — while it claims to deliver 'validated responses', the specific evaluation, drift detection, and observability guardrails used to verify financial accuracy are not detailed.

L6 · Security & Compliance (cross-cutting)✓ mapped

Operating in 'heavily regulated banks' makes security and compliance paramount. Key threats include compliance violations (e.g., GLBA, GDPR) if sensitive banker conversations contain PII, and a lack of robust audit logging for LLM interactions.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — there is no mention of multi-agent orchestration or external marketplace integrations, meaning ecosystem threats are currently minimal.

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