← RAW@AI - Risk Management Advisor
RAW@AI - Risk Management Advisor — agentic threat model
RAW@AI acts as an advisory agent processing highly sensitive corporate risk registers, contracts, and insurance policies. While its direct operational autonomy is low, a compromise poses significant confidentiality risks due to the proprietary business data it analyzes.
OWASP AIVSS score rationale
| Autonomy of Action | 0.30 | |
| Goal-Driven Planning | 0.40 | |
| Self-Modification | 0.00 | |
| Dynamic Tool Use | 0.40 | |
| Persistent Memory | 0.20 | |
| Contextual Awareness | 0.60 | |
| Dynamic Identity | 0.00 | |
| Multi-Agent Interactions | 0.10 | |
| Non-Determinism | 0.50 | |
| Opacity & Reflexivity | 0.40 |
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 specific foundation models used for risk description generation and pre-training are not disclosed, leaving potential exposure to model-specific adversarial prompt injection or extraction risks.
Not certain from the listing — the platform processes sensitive risk registers, contracts, and insurance policies, but the storage, vectorization, and data isolation mechanisms for these documents are unspecified.
Not certain from the listing — the orchestration framework managing the transition between risk identification, Monte-Carlo simulations, and document auditing is not detailed.
Not certain from the listing — hosting infrastructure, tenant isolation, and sandboxing for running quantitative simulations (like Monte-Carlo) are not described.
Not certain from the listing — there is no mention of real-time guardrails, output validation, or logging mechanisms to detect hallucinated risk advice or biased simulation parameters.
Not certain from the listing — compliance certifications (such as SOC2 or ISO 27001) and access control policies for multi-tenant risk data are not cited.
Not certain from the listing — the agent operates primarily as a standalone virtual advisor, with no explicit multi-agent coordination or external ecosystem integrations mentioned.
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.