AgentReadyHomeAgent Listing

← Yahoo Finance MCP

Yahoo Finance MCP — agentic threat model

5.7AIVSS 5.7 · Medium

A low-risk, read-only financial data tool wrapper whose primary security concern is indirect prompt injection from untrusted news text fetched from Yahoo Finance.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 5.3AARS uplift 0.38Factor sum 0.8/10Threat ×1.0Mitigation ×1.0
Autonomy of Action
0.10
Goal-Driven Planning
0.10
Self-Modification
0.00
Dynamic Tool Use
0.10
Persistent Memory
0.00
Contextual Awareness
0.10
Dynamic Identity
0.00
Multi-Agent Interactions
0.10
Non-Determinism
0.20
Opacity & Reflexivity
0.10

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 MCP server does not include a model, but the calling LLM is vulnerable to indirect prompt injection via untrusted news text returned by the API.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — Data is fetched dynamically from Yahoo Finance; there is no local vector store, but upstream data poisoning remains a theoretical risk.

L3 · Agent Frameworks✓ mapped

The tool surface is strictly read-only financial queries, minimizing tool misuse risks, though the returned news text represents untrusted input that could trigger indirect prompt injection in the calling framework.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — Host security and sandboxing depend entirely on the user's deployment environment, though internet egress is required to fetch financial data.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — No logging, monitoring, or input-filtering guardrails are described in this open-source wrapper.

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

The tool requires no authentication and accesses only public market data, resulting in a low compliance and authorization security surface.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — While it can be integrated into multi-agent systems via MCP, the server itself does not establish agent-to-agent trust or coordination protocols.

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