AgentReadyHomeAgent Listing

← AKShare One MCP

AKShare One MCP — agentic threat model

4.5AIVSS 4.5 · Medium

The AKShare One MCP agent is a read-only financial data connector with low agentic risk, primarily acting as an informational tool rather than an autonomous decision-maker.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 4.3AARS uplift 0.65Factor sum 1.2/10Threat ×0.95Mitigation ×0.9
Autonomy of Action
0.10
Goal-Driven Planning
0.10
Self-Modification
0.00
Dynamic Tool Use
0.20
Persistent Memory
0.00
Contextual Awareness
0.30
Dynamic Identity
0.00
Multi-Agent Interactions
0.10
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 underlying foundation model is not specified. However, the model is susceptible to prompt injection if downstream systems process the returned financial news or market data without sanitization.

L2 · Data Operations✓ mapped

The agent pulls external market data via AKShare. The primary threat is data poisoning or manipulation of the external financial feeds, which could lead downstream systems to make incorrect financial decisions.

L3 · Agent Frameworks✓ mapped

The agent framework exposes read-only tools for historical/real-time prices and news. Risks include insecure tool integration where downstream agents execute actions based on unvalidated financial inputs.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — The deployment environment (local MCP host or container) is unspecified. Standard risks include exposed local ports or lack of network sandboxing for the MCP server.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — No built-in evaluation, logging, or guardrails are mentioned. There is a risk of silent failures or data drift in the underlying AKShare API feeds.

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

The agent is open-source and free, with no explicit authentication or authorization mechanisms mentioned. It relies on the host environment's security policies.

L7 · Agent Ecosystem✓ mapped

As an MCP tool, this agent is designed to be called by other agents. The primary ecosystem threat is cascading failures where other agents trust this data implicitly for automated trading or analysis.

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