AgentReadyHomeAgent Listing

← Marb.ai

Marb.ai — agentic threat model

9.2AIVSS 9.2 · Critical

Marb.ai presents a moderate-to-high risk profile due to its integration with sensitive CRM data, automated email/chat processing, and capability to draft financial offers, making it highly susceptible to indirect prompt injection and data exfiltration.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 8.2AARS uplift 1.0Factor sum 5.3/10Threat ×1.05Mitigation ×1.0
Autonomy of Action
0.70
Goal-Driven Planning
0.60
Self-Modification
0.10
Dynamic Tool Use
0.50
Persistent Memory
0.60
Contextual Awareness
0.80
Dynamic Identity
0.20
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.

L1 · Foundation Models⚠ not certain from listing

Not certain from the listing — likely utilizes commercial LLMs combined with a proprietary speech-to-text model fine-tuned on real estate jargon. Primary threats include prompt injection via incoming emails/chats and model hallucinations when drafting property offers.

L2 · Data Operations✓ mapped

Utilizes vector-based similarity search across a global property database and processes buyer profiles. Key threats include vector database poisoning, embedding inversion, and unauthorized exfiltration of sensitive buyer PII.

L3 · Agent Frameworks✓ mapped

Orchestrates automated research, task extraction from voice/emails, and CRM API integration. Vulnerable to indirect prompt injection where malicious text in emails or chats triggers unauthorized CRM tool execution or data manipulation.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — likely hosted on cloud infrastructure to support 24/7 background research and API integrations. Risks include insecure storage of CRM API keys and lack of sandboxing when processing untrusted voice/text inputs.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — no mention of continuous monitoring, guardrails, or drift detection. Risks include undetected drift in property matching algorithms or unmonitored generation of inappropriate/unauthorized follow-up communications.

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

Not certain from the listing — no explicit compliance certifications (e.g., SOC 2, GDPR) or fine-grained RBAC mentioned. Risks include unauthorized access to the CRM integration and non-compliance with data privacy regulations regarding buyer PII.

L7 · Agent Ecosystem✓ mapped

Employs multiple AI agents for 24/7 research and integrates with external CRM ecosystems. Risks include cascading failures if the CRM API changes, and trust abuse between the research agents and the main assistant agent.

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