AgentReadyHomeAgent Listing

← claude-d3js-skill

claude-d3js-skill — agentic threat model

6.5AIVSS 6.5 · Medium

The agent is a low-risk code-generation skill with minimal autonomy, but poses a potential indirect risk of generating malicious or vulnerable d3.js code (such as Cross-Site Scripting) if prompt-injected or fed untrusted data.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 6.1AARS uplift 0.39Factor sum 1.0/10Threat ×1.0Mitigation ×1.0
Autonomy of Action
0.10
Goal-Driven Planning
0.10
Self-Modification
0.00
Dynamic Tool Use
0.00
Persistent Memory
0.00
Contextual Awareness
0.20
Dynamic Identity
0.00
Multi-Agent Interactions
0.00
Non-Determinism
0.40
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✓ mapped

Relies on Claude as the foundation model. Primary threats include prompt injection that could force the model to generate malicious JavaScript (XSS) disguised as valid d3.js visualization code.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — No dedicated data operations, RAG, or vector stores are mentioned; it likely processes user-provided datasets in-context to generate d3.js data bindings.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — It is described as a 'skill' rather than a full framework, meaning orchestration, memory, and tool-calling are likely handled by the parent Claude platform.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — No hosting or sandboxing details are provided; the generated d3.js code is executed by the end-user, shifting execution risk to the client browser.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — No monitoring, logging, or guardrails are specified for validating the safety of the generated JavaScript code.

L6 · Security & Compliance (cross-cutting)⚠ not certain from listing

Not certain from the listing — Lacks explicit identity, authorization, or compliance controls, relying entirely on the host platform's security posture.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — No multi-agent interactions or marketplace integrations are described for this standalone visualization skill.

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