AgentReadyHomeAgent Listing

← HubSpot MCP Server

HubSpot MCP Server — agentic threat model

7.6AIVSS 7.6 · High

The HubSpot MCP Server presents a high-risk profile due to its direct read/write access to sensitive CRM data and customer PII, though this risk is partially mitigated by OAuth and private-app token scoping.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 8.5AARS uplift 0.46Factor sum 3.1/10Threat ×1.0Mitigation ×0.85
Autonomy of Action
0.50
Goal-Driven Planning
0.10
Self-Modification
0.00
Dynamic Tool Use
0.70
Persistent Memory
0.20
Contextual Awareness
0.30
Dynamic Identity
0.40
Multi-Agent Interactions
0.50
Non-Determinism
0.20
Opacity & Reflexivity
0.20

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 listing describes an MCP server providing tools rather than the underlying foundation model itself, leaving model-specific vulnerabilities (e.g., prompt injection susceptibility) undefined.

L2 · Data Operations✓ mapped

Directly handles sensitive CRM data operations, exposing customer PII, deals, and tickets. This creates a high risk of data exfiltration or unauthorized modification of the system of record.

L3 · Agent Frameworks✓ mapped

Exposes powerful tools to search, create, and update CRM objects. Insecure tool integration or malicious tool-use prompts could lead to bulk deletion or corruption of CRM records.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — The hosting environment, network isolation, and secure storage of OAuth client secrets or private-app tokens are not detailed in the directory listing.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — There is no mention of transaction logging, auditability of tool executions, or real-time guardrails to detect anomalous CRM queries.

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

Leverages OAuth and private-app token scopes to enforce authorization boundaries, ensuring the MCP server's access is restricted to specified CRM permissions.

L7 · Agent Ecosystem✓ mapped

Acts as an MCP utility server designed to be called by other agents. This introduces agent-to-agent trust risks, where a compromised orchestrator agent could abuse this server to extract CRM data.

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