Callyourgirlfriend — agentic threat model
Callyourgirlfriend is a static directory and review website with minimal agentic risk, as it does not perform autonomous actions, execute tools, or handle sensitive user data directly.
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 platform appears to be a static review directory rather than an active LLM-driven agent, meaning foundation model threats like adversarial prompt injection or model reprogramming are likely inapplicable unless a search chatbot is integrated.
Not certain from the listing — Data operations likely consist of a standard content management system (CMS) or static database of human-tested reviews. Risk of vector database poisoning or embedding inversion is extremely low unless RAG is used for user queries.
Not certain from the listing — There is no evidence of an active agent orchestration framework (e.g., LangChain, AutoGen) or tool-calling capabilities, making tool misuse and memory poisoning threats irrelevant.
Not certain from the listing — Standard web hosting infrastructure threats apply (e.g., CMS vulnerabilities, DDoS, or unauthorized access to the web server), but there are no complex agent sandboxing requirements.
Not certain from the listing — Observability is likely limited to standard web analytics (e.g., Google Analytics) rather than LLM guardrails, evaluation frameworks, or real-time drift detection.
Not certain from the listing — Compliance requirements are minimal, primarily focusing on standard web privacy policies (GDPR/CCPA) for site visitors, with no complex AI-specific governance needed.
Not certain from the listing — The platform operates as a standalone directory with no multi-agent orchestration, marketplace integrations, or agent-to-agent communication channels.
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.