AgentReadyHomeAgent ListingPricing

← Skuno

Skuno — agentic threat model

9.0AIVSS 9.0 · Critical

Skuno presents a high-risk profile due to its deep integration with critical enterprise systems like Microsoft Dynamics 365 Business Central and POS networks. A compromise could lead to unauthorized financial transactions, inventory manipulation, and sensitive data exfiltration.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 8.5AARS uplift 0.52Factor sum 3.3/10Threat ×1.05Mitigation ×1.0
Autonomy of Action
0.60
Goal-Driven Planning
0.30
Self-Modification
0.00
Dynamic Tool Use
0.80
Persistent Memory
0.20
Contextual Awareness
0.50
Dynamic Identity
0.10
Multi-Agent Interactions
0.00
Non-Determinism
0.30
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 — The specific foundation models powering Skuno's analytics and reporting are not disclosed. Potential risks include prompt injection leading to manipulated financial reports or inventory data leakage.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — The data pipeline architecture between POS, warehouses, and Dynamics 365 is not detailed. The primary threat is data poisoning of inventory or sales records, which could disrupt supply chains or financial reporting.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — The orchestration framework is proprietary. Insecure tool integration is a major threat, as the agent calls APIs to modify inventory levels and process sales transactions in Dynamics 365.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — Hosting and deployment environments are not specified. Compromise of the hosting infrastructure could allow attackers to intercept API keys and credentials used to access the ERP system.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — No observability or guardrail mechanisms are mentioned. A lack of continuous monitoring could allow silent drift or malicious manipulation of automated inventory syncs to go unnoticed.

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

Not certain from the listing — No compliance certifications (e.g., SOC 2, PCI-DSS) are cited despite handling POS and financial data. Weak access controls or lack of audit logging within the agent could violate financial compliance standards.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — There is no mention of multi-agent collaboration or external agent marketplaces. The primary ecosystem risk is cascading failures across the connected POS and ERP networks if the agent is compromised.

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

These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology. Are you the vendor? Factual corrections are free.