Kibu — agentic threat model
Kibu presents a low-to-moderate agentic risk profile as it primarily functions as a document generation and compliance aid for disability service providers, though the sensitivity of the underlying data (potentially containing PII or health-related context) elevates the impact of potential data exposure.
OWASP AIVSS score rationale
| Autonomy of Action | 0.20 | |
| Goal-Driven Planning | 0.20 | |
| Self-Modification | 0.00 | |
| Dynamic Tool Use | 0.10 | |
| Persistent Memory | 0.30 | |
| Contextual Awareness | 0.40 | |
| Dynamic Identity | 0.00 | |
| Multi-Agent Interactions | 0.00 | |
| Non-Determinism | 0.40 | |
| Opacity & Reflexivity | 0.30 |
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 by Kibu are not disclosed. Standard risks include prompt injection altering educational content or compliance templates, and potential model bias affecting disability-related recommendations.
Not certain from the listing — Kibu processes provider documentation and compliance data, which likely involves a RAG pipeline or vector database. The primary threat is the leakage or poisoning of sensitive provider and client data within these data stores.
Not certain from the listing — The orchestration framework is not specified. Risks involve insecure tool integration if the agent connects directly to provider databases or external compliance APIs to pull or push documentation.
Not certain from the listing — Deployment architecture is not detailed. As an open-source and freemium platform, hosting environments must be secured against unauthorized access, especially given the sensitive nature of disability service records.
Not certain from the listing — No evaluation or observability stack is mentioned. Guardrails are critical here to prevent the generation of inappropriate educational content or inaccurate compliance documentation.
Not certain from the listing — While Kibu is designed to keep organizations 'audit-ready', the listing does not detail its internal security controls, access management, or compliance with standards like HIPAA or GDPR which are highly relevant to disability service providers.
Not certain from the listing — There is no indication of multi-agent orchestration or external agent marketplace integration in Kibu's current feature set.
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.