AgentReadyHomeAgent Listing

← CanvasAI

CanvasAI — agentic threat model

8.7AIVSS 8.7 · High

CanvasAI presents a moderate-to-high agentic risk due to its deep integration with enterprise customer data sources and its ability to trigger automated workflows. A compromise could lead to sensitive customer data exfiltration or unauthorized automated actions affecting B2B customer relationships.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 7.5AARS uplift 1.15Factor sum 4.6/10Threat ×1.0Mitigation ×1.0
Autonomy of Action
0.60
Goal-Driven Planning
0.50
Self-Modification
0.10
Dynamic Tool Use
0.60
Persistent Memory
0.50
Contextual Awareness
0.80
Dynamic Identity
0.20
Multi-Agent Interactions
0.20
Non-Determinism
0.50
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 — The underlying foundation models are not specified. Standard LLM risks such as prompt injection, jailbreaking, and indirect prompt injection via customer data sources remain a baseline threat.

L2 · Data Operations✓ mapped

CanvasAI consolidates data from multiple enterprise sources to detect risks and opportunities. This creates a high-value target for data exfiltration, unauthorized access, and data poisoning if malicious data is ingested from a connected CRM or database.

L3 · Agent Frameworks✓ mapped

The platform features 'Canvas Copilot' for complex task handling and automated workflows. Insecure tool integration or prompt injection could allow an attacker to trigger unauthorized workflows, send rogue emails, or manipulate customer records.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — The deployment architecture, hosting environment, and sandboxing mechanisms for executing automated workflows are not described.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — There is no mention of built-in guardrails, observability tools, or logging mechanisms to detect anomalous agent behavior or drift in risk-detection models.

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

Not certain from the listing — While designed for enterprise customer success, the listing does not explicitly cite compliance certifications (e.g., SOC 2, GDPR) or detail the RBAC model governing data access.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — The agent operates primarily as a centralized platform; there is no explicit mention of multi-agent orchestration or marketplace integrations.

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