Sexual AI Directory — agentic threat model
The Sexual AI Directory is a curated directory of NSFW AI tools rather than an active autonomous agent, presenting minimal agentic risk but carrying standard web-based privacy and redirection risks.
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 | 0.10 | |
| Dynamic Identity | 0.00 | |
| Multi-Agent Interactions | 0.00 | |
| Non-Determinism | 0.10 | |
| Opacity & Reflexivity | 0.10 |
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 directory itself may not utilize a foundation model directly, or may only use one offline for generating reviews, meaning direct LLM vulnerabilities like prompt injection are likely non-applicable.
Not certain from the listing — It is unclear if the directory uses a vector database or RAG for search. The primary data risk is the integrity of the curated links and reviews database.
Not certain from the listing — There is no evidence of an active agent framework or orchestration layer; the platform operates as a standard informational directory.
Not certain from the listing — Standard web hosting and infrastructure risks apply, such as server compromise or database exposure, which could lead to defacement or malicious link injection.
Not certain from the listing — No evaluation, observability, or content guardrails are mentioned for verifying the safety or ongoing validity of the external links listed.
Not certain from the listing — No security, compliance, or privacy-preserving controls are detailed, which is a potential concern given the sensitive nature of NSFW directory browsing.
Not certain from the listing — While the directory indexes other AI agents and interactive tools, it does not programmatically interact with them, eliminating multi-agent cascading failure risks.
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.