Greatlooks AI — agentic threat model
Greatlooks AI presents a moderate risk profile primarily driven by its handling of sensitive personal health information (PHI) and multi-channel communication capabilities (WhatsApp, email, voice) without explicit security or compliance guarantees.
OWASP AIVSS score rationale
| Autonomy of Action | 0.30 | |
| Goal-Driven Planning | 0.20 | |
| Self-Modification | 0.00 | |
| Dynamic Tool Use | 0.30 | |
| Persistent Memory | 0.60 | |
| Contextual Awareness | 0.50 | |
| Dynamic Identity | 0.10 | |
| Multi-Agent Interactions | 0.00 | |
| Non-Determinism | 0.50 | |
| Opacity & Reflexivity | 0.60 |
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 — likely utilizes commercial LLMs to power its 24/7 virtual beauty consultant. Key threats include prompt injection that could bypass safety filters to deliver unauthorized or harmful medical/recovery advice.
Not certain from the listing — relies on a proprietary database of vetted clinics and specialists alongside user-provided budget and location data. Threats include database poisoning to promote unvetted clinics and exfiltration of sensitive user cosmetic goals.
Not certain from the listing — orchestrates user journeys across multiple channels (web, email, WhatsApp, voice). Threats include insecure tool integration with communication APIs, potentially allowing session hijacking or spoofed messaging.
Not certain from the listing — hosted as a closed-source SaaS platform. Threats include exposure of API keys for third-party messaging channels and lack of isolation between user sessions.
Not certain from the listing — no guardrails or observability tools are mentioned. This creates a risk of undetected drift where the AI provides inaccurate post-procedure care instructions.
Not certain from the listing — handles sensitive health-related inquiries but does not specify HIPAA, GDPR, or SOC2 compliance, posing significant regulatory and data privacy risks.
Not certain from the listing — operates as a standalone vertical agent with no explicit multi-agent orchestration, limiting ecosystem-specific cascading 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.