AgentReadyHomeAgent Listing

← NooksAI

NooksAI — agentic threat model

8.8AIVSS 8.8 · High

NooksAI presents a moderate-to-high agentic risk profile due to its deep integration with enterprise CRMs, email systems, and telephony infrastructure. A compromise could lead to automated spam/phishing campaigns, CRM data theft, or unauthorized communication.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 8.5AARS uplift 0.76Factor sum 4.8/10Threat ×1.05Mitigation ×0.95
Autonomy of Action
0.60
Goal-Driven Planning
0.50
Self-Modification
0.10
Dynamic Tool Use
0.70
Persistent Memory
0.60
Contextual Awareness
0.70
Dynamic Identity
0.30
Multi-Agent Interactions
0.20
Non-Determinism
0.60
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⚠ not certain from listing

Not certain from the listing — likely relies on third-party LLMs for email generation and transcription. Risks include prompt injection leading to malicious email generation or data leakage.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — processes sensitive CRM data, call recordings, and prospect info. Risks include data exfiltration, unauthorized access to call transcripts, and lack of data lineage.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — orchestrates dialing, email generation, and CRM updates. Risks include insecure tool integration with CRMs and email gateways, allowing unauthorized actions.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — hosted cloud platform with mobile access. Risks include insecure API endpoints, credential theft for CRM integrations, and lack of sandboxing for execution environments.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — provides call analytics and transcription. Risks include insufficient logging of AI-generated email content and lack of guardrails against generating toxic or non-compliant sales pitches.

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

Not certain from the listing — handles PII and sales data, requiring compliance with TCPA (for dialing), GDPR/CCPA, and SOC2. Risks include unauthorized access to customer contact details.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — integrates with external CRM and marketing automation tools. Risks include cascading failures if connected CRM APIs are compromised or rate-limited.

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