AgentReadyHomeAgent Listing

← Facebook Ads MCP Server

Facebook Ads MCP Server — agentic threat model

9.1AIVSS 9.1 · Critical

This agent acts as a high-value bridge to the Meta Marketing API, carrying significant risk of unauthorized financial spend, campaign manipulation, and sensitive marketing data exfiltration if compromised.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 8.5AARS uplift 0.58Factor sum 3.7/10Threat ×1.05Mitigation ×1.0
Autonomy of Action
0.40
Goal-Driven Planning
0.30
Self-Modification
0.00
Dynamic Tool Use
0.80
Persistent Memory
0.10
Contextual Awareness
0.50
Dynamic Identity
0.70
Multi-Agent Interactions
0.20
Non-Determinism
0.40
Opacity & Reflexivity
0.30

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 itself is model-agnostic and does not specify a foundation model, though it is vulnerable to indirect prompt injection via the LLM that orchestrates it.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — there is no explicit RAG or vector database mentioned, but the server handles sensitive marketing performance and spend data retrieved dynamically from the Meta API.

L3 · Agent Frameworks✓ mapped

The agent framework layer is highly exposed; insecure tool integration or prompt injection could lead to unauthorized tool execution, such as modifying campaigns or altering ad spend parameters.

L4 · Deployment & Infrastructure✓ mapped

The deployment infrastructure must securely store and handle a highly sensitive Meta access token with ads scope; exposure of this token leads to complete account compromise.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — there are no mentioned logging, auditing, or guardrail mechanisms to monitor API calls or detect anomalous spending/campaign changes initiated by the agent.

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

The agent relies on the Meta Marketing API's OAuth/token permissions. If the token scope is not strictly limited to read-only, it bypasses traditional write-access authorization controls.

L7 · Agent Ecosystem✓ mapped

As an MCP server, this tool is designed to be called by other agents, creating a risk of cascading failures or unauthorized access if a compromised upstream agent invokes its tools.

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