Flirty AI — agentic threat model
Flirty AI is primarily an informational directory and aggregator for NSFW chatbots rather than an active agentic system, presenting low operational risk but high privacy risks regarding sensitive user preferences and potential redirection to malicious third-party platforms.
OWASP AIVSS score rationale
| Autonomy of Action | 0.10 | |
| Goal-Driven Planning | 0.00 | |
| Self-Modification | 0.00 | |
| Dynamic Tool Use | 0.00 | |
| Persistent Memory | 0.10 | |
| Contextual Awareness | 0.20 | |
| 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.
Not certain from the listing — The directory aggregates third-party chatbots, meaning the underlying foundation models are external and unknown, presenting risks of misaligned outputs, bias, or adversarial prompt injection.
Not certain from the listing — The platform stores categorized prompts, reviews, and potentially user accounts, which risks data exfiltration of highly sensitive NSFW user preferences and interaction history.
Not certain from the listing — No specific orchestration framework is mentioned for the directory itself, though the indexed chatbots likely rely on basic conversational frameworks with minimal tool integration.
Not certain from the listing — The hosting, sandboxing, and network infrastructure for both the directory and the external chatbot platforms are unspecified, leaving potential vectors for web-based compromise.
Not certain from the listing — There is no mention of content filtering, input/output guardrails, or observability tools to monitor the safety of the aggregated chatbot interactions.
Not certain from the listing — No explicit identity management, age verification, or privacy compliance controls (such as GDPR for sensitive adult data) are detailed in the directory listing.
Flirty AI acts as a directory and marketplace ecosystem for third-party chatbots, introducing significant ecosystem risks where users may be redirected to rogue, malicious, or compromised external chat agents.
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.