Nordcraft — agentic threat model
Nordcraft presents a moderate security risk as an AI-assisted website builder with API and GraphQL integration. The primary threat lies in the potential for prompt injection to generate malicious code (XSS) or execute unauthorized API queries, mitigated primarily by the visual, human-in-the-loop editing interface.
OWASP AIVSS score rationale
| Autonomy of Action | 0.40 | |
| Goal-Driven Planning | 0.50 | |
| Self-Modification | 0.10 | |
| Dynamic Tool Use | 0.60 | |
| Persistent Memory | 0.30 | |
| Contextual Awareness | 0.50 | |
| Dynamic Identity | 0.20 | |
| Multi-Agent Interactions | 0.20 | |
| Non-Determinism | 0.60 | |
| Opacity & Reflexivity | 0.40 |
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 — The underlying foundation models are not specified. Standard risks like prompt injection leading to malicious code generation or unauthorized API calls apply.
Not certain from the listing — While it supports live data design and API/GraphQL connections, the data storage, vector databases, or training data operations are not detailed.
Not certain from the listing — The orchestration framework is proprietary. However, the agent's ability to execute logic workflows and trigger API/GraphQL connections introduces risks of tool misuse and insecure tool integration if inputs are not sanitized.
Not certain from the listing — The hosting, sandboxing of generated code, and secrets management for API/GraphQL keys are not disclosed.
Not certain from the listing — There is no mention of real-time monitoring, guardrails, or logging mechanisms to detect malicious prompt injections or anomalous API requests.
Not certain from the listing — Although team collaboration is supported (implying some access control), specific security certifications, compliance alignments, or audit logging are not detailed.
Not certain from the listing — The platform does not explicitly describe a multi-agent ecosystem or marketplace interactions, though team collaboration features could introduce multi-user trust boundaries.
MAESTRO — the 7-layer agentic threat-modeling framework (Cloud Security Alliance / Ken Huang).
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology. Are you the vendor? Factual corrections are free.