AgentReadyHomeAgent Listing

← MCPVault (Obsidian)

MCPVault (Obsidian) — agentic threat model

7.3AIVSS 7.3 · High

MCPVault presents a moderate-to-high risk profile due to its direct read/write access to local markdown files, making robust path scoping and write consent mechanisms critical to preventing unauthorized data exfiltration or modification.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 7.8AARS uplift 0.75Factor sum 3.4/10Threat ×1.0Mitigation ×0.85
Autonomy of Action
0.60
Goal-Driven Planning
0.30
Self-Modification
0.10
Dynamic Tool Use
0.70
Persistent Memory
0.50
Contextual Awareness
0.40
Dynamic Identity
0.10
Multi-Agent Interactions
0.20
Non-Determinism
0.30
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 does not specify which foundation model is used, as MCPVault is an MCP server designed to interface with external LLM clients.

L2 · Data Operations✓ mapped

Directly operates on local markdown files within an Obsidian vault. Key risks include unauthorized local data exfiltration, knowledge-base corruption, and path traversal if path scoping is bypassed.

L3 · Agent Frameworks✓ mapped

Exposes 14 tools for reading, writing, and searching notes. Vulnerable to tool misuse if an LLM client is manipulated into executing destructive write or delete operations across the vault.

L4 · Deployment & Infrastructure✓ mapped

Runs as a local server. Risks include local privilege escalation or unauthorized filesystem access if the server process is compromised or lacks proper sandboxing.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — There is no mention of built-in logging, auditing, or real-time monitoring of tool execution within the MCP server itself.

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

Identifies path scoping and write consent as key security considerations, but relies on the user or client configuration to enforce these access control policies.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — While designed to integrate into an MCP-compatible ecosystem, specific multi-agent trust boundaries or cascading failure mitigations are not detailed.

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