AgentReadyHomeAgent Listing

← Photo3D

Photo3D — agentic threat model

7.2AIVSS 7.2 · High

Photo3D exhibits low agentic risk due to its limited autonomy, lack of multi-step planning, and focus on human-in-the-loop 3D asset generation. The primary security concerns center around intellectual property protection of uploaded/generated assets and the secure parsing of 3D file formats.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 6.5AARS uplift 0.67Factor sum 1.9/10Threat ×1.0Mitigation ×1.0
Autonomy of Action
0.20
Goal-Driven Planning
0.10
Self-Modification
0.00
Dynamic Tool Use
0.20
Persistent Memory
0.20
Contextual Awareness
0.10
Dynamic Identity
0.00
Multi-Agent Interactions
0.00
Non-Determinism
0.60
Opacity & Reflexivity
0.50

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 — likely uses proprietary or open-source 2D-to-3D diffusion or reconstruction models. Threats include adversarial image inputs causing generation failures, or model extraction/stealing of the specialized 3D generation weights.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — requires ingestion of user-uploaded reference images and storage of generated GLB/3D assets. Threats include data exfiltration of proprietary designs and potential poisoning of training datasets if user uploads are used for continuous model training.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — likely uses a basic pipeline orchestrator rather than a complex agentic framework. Threats include insecure handling of file conversion tools or vulnerabilities in the libraries used for 3D format conversion (e.g., GLB/OBJ parsing).

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — hosted AI generation requires GPU-enabled cloud infrastructure. Threats include container escape during heavy 3D rendering/conversion workloads or unauthorized access to hosted asset storage buckets.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — likely relies on manual human inspection via the browser-based 3D tool rather than automated evaluation. Threats include a lack of automated validation for corrupted, malformed, or malicious 3D model outputs.

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

Not certain from the listing — standard web authentication and team role-based access control (RBAC) are expected but unverified. Threats include unauthorized access to team projects and intellectual property leakage due to weak access controls.

L7 · Agent Ecosystem✓ mapped

The agent operates as a standalone horizontal creative tool with no described multi-agent or marketplace integrations, making ecosystem-level cascading failures or rogue agent interactions highly unlikely.

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