Genjutsu AI — agentic threat model
Genjutsu AI is a low-risk, single-purpose generative content tool with zero agentic autonomy, planning, or tool-use capabilities. Its primary security risks are limited to prompt injection for content filter bypass (e.g., generating deepfakes or NSFW media) and credit-theft/billing abuse.
OWASP AIVSS score rationale
| Autonomy of Action | 0.00 | |
| Goal-Driven Planning | 0.00 | |
| Self-Modification | 0.00 | |
| Dynamic Tool Use | 0.00 | |
| Persistent Memory | 0.00 | |
| Contextual Awareness | 0.00 | |
| Dynamic Identity | 0.00 | |
| Multi-Agent Interactions | 0.00 | |
| Non-Determinism | 0.70 | |
| Opacity & Reflexivity | 0.00 |
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.
Uses Seedance 2.0, Seedance 2.0 Fast, and GPT Image 2. Primary threats include prompt injection to bypass safety filters (leading to NSFW, copyright-infringing, or deepfake generation) and model output misalignment.
Not certain from the listing — No details are provided about training data, vector stores, or RAG. Potential threats include poisoning of downstream caches or exfiltration of user-uploaded reference images if supported.
The agent framework is minimal or non-existent, with no planning, memory, or tool calling. Threats are extremely low, limited to basic prompt routing and credit validation logic.
Not certain from the listing — The hosting environment (cloud/SaaS) is unspecified. Standard web application threats apply, such as container compromise, API key exposure for third-party models, and credit-system bypasses.
Not certain from the listing — No mention of guardrails, output filtering, or logging. Lack of input/output moderation could allow generation of harmful, copyrighted, or deepfake content.
Not certain from the listing — Identity and access management details are omitted beyond basic user accounts. Compliance risks include copyright infringement of generated media and lack of clear data retention policies.
No multi-agent or marketplace interactions are supported. Threat is negligible as it operates as an isolated single-user tool.
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 — every score is re-derived by the same automated method as an agent's public evidence changes.