AI Genogram Maker — agentic threat model
The AI Genogram Maker exhibits low agentic risk due to its limited autonomy and lack of external system integrations, but presents a high data privacy risk because it processes highly sensitive therapeutic and family relationship data.
OWASP AIVSS score rationale
| Autonomy of Action | 0.20 | |
| Goal-Driven Planning | 0.20 | |
| Self-Modification | 0.00 | |
| Dynamic Tool Use | 0.20 | |
| Persistent Memory | 0.10 | |
| Contextual Awareness | 0.40 | |
| Dynamic Identity | 0.00 | |
| Multi-Agent Interactions | 0.00 | |
| Non-Determinism | 0.50 | |
| 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.
Not certain from the listing — likely uses a multimodal foundation model to process both plain-language descriptions and uploaded images. Primary threats include prompt injection via user-provided family descriptions or adversarial image uploads designed to manipulate the generated relationship patterns or bypass safety filters.
Not certain from the listing — states that family data is 'encrypted & private' but does not detail the storage architecture or whether RAG is utilized. Threats include unauthorized access to stored family trees, image uploads, and potential data leakage if user inputs are cached or used for downstream model fine-tuning.
Not certain from the listing — likely uses a basic orchestration framework to translate LLM outputs into structured diagram formats (SVG/PNG/PDF). Threats include insecure tool integration, particularly within the PDF/image generation libraries which are historically prone to local file inclusion or remote code execution.
Not certain from the listing — hosting details are unspecified. Standard web application threats apply, with elevated risk around the sandboxing of image-parsing and PDF-rendering microservices which could be targeted for container escape.
Not certain from the listing — no evaluation, guardrails, or observability mechanisms are mentioned. The lack of visible guardrails increases the risk of generating biased, offensive, or clinically inaccurate relationship analyses without administrator detection.
As a 'HealthTech' tool used by therapists, counselors, and social workers, the agent handles highly sensitive personal and potentially health-related data (PHI). Compliance with regulations like HIPAA or GDPR is critical, and despite claims of being 'encrypted & private', the lack of formal certifications (e.g., SOC2) represents a compliance gap.
The agent operates as a standalone, single-user utility with no described multi-agent coordination, marketplace integrations, or external agent-to-agent communication, making ecosystem-level threats negligible.
MAESTRO — the 7-layer agentic threat-modeling framework (Cloud Security Alliance / Ken Huang).