Orby AI — agentic threat model
Orby AI acts as an automated digital worker, presenting high agentic risk due to its potential access to sensitive enterprise applications and user sessions, combined with a lack of visible security controls in the public listing.
OWASP AIVSS score rationale
| Autonomy of Action | 0.70 | |
| Goal-Driven Planning | 0.50 | |
| Self-Modification | 0.10 | |
| Dynamic Tool Use | 0.80 | |
| Persistent Memory | 0.60 | |
| Contextual Awareness | 0.70 | |
| Dynamic Identity | 0.60 | |
| Multi-Agent Interactions | 0.30 | |
| 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 relies on proprietary or commercial Vision-Language Models (VLMs) to interpret user screens and automate tasks, exposing it to visual prompt injection and adversarial UI manipulation.
Not certain from the listing — likely captures and processes user interaction data, screen recordings, and enterprise inputs to automate workflows, raising significant risks of sensitive data exposure or PII leakage.
Not certain from the listing — utilizes an orchestration framework to translate natural language or demonstrations into UI actions. Vulnerable to action hijacking if malicious inputs manipulate the execution flow.
Not certain from the listing — likely deployed as a local desktop agent or cloud service with deep integration into user environments, presenting risks of privilege escalation or session hijacking if compromised.
Not certain from the listing — requires comprehensive audit logging and real-time monitoring of automated actions to detect unauthorized activities or silent workflow failures.
Not certain from the listing — closed-source nature limits external verification of enterprise compliance, access controls, and data isolation policies.
Not certain from the listing — potential risk if the digital worker interacts with external APIs, third-party integrations, or other automated agents without strict boundary controls.
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.