AgentReadyHomeAgent Listing

← KODIF

KODIF — agentic threat model

8.0AIVSS 8.0 · High

KODIF presents a moderate risk profile primarily driven by its capability to autonomously generate knowledge base articles and execute customer support policies, which could lead to automated misinformation or customer data exposure if compromised.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 6.3AARS uplift 1.67Factor sum 4.5/10Threat ×1.0Mitigation ×1.0
Autonomy of Action
0.60
Goal-Driven Planning
0.50
Self-Modification
0.20
Dynamic Tool Use
0.40
Persistent Memory
0.50
Contextual Awareness
0.70
Dynamic Identity
0.20
Multi-Agent Interactions
0.30
Non-Determinism
0.60
Opacity & Reflexivity
0.50

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.

L1 · Foundation Models⚠ not certain from listing

Not certain from the listing — The underlying foundation models are not specified. Standard LLM risks such as prompt injection, hallucinated outputs, and adversarial manipulation apply, especially since users can configure agents using natural language.

L2 · Data Operations✓ mapped

The agent performs knowledge gap detection and KB article generation, indicating ingestion of customer support data and interaction with a knowledge base. This introduces risks of data poisoning (injecting malicious info into the KB) and sensitive data exfiltration from customer histories.

L3 · Agent Frameworks✓ mapped

KODIF allows building AI agents using natural language policies. This orchestration layer is vulnerable to indirect prompt injection where customer inputs bypass the natural language policies, leading to unintended tool execution or policy violations.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — As a closed-source, paid SaaS technology, the hosting environment, sandboxing of agent execution, and secrets management are not disclosed.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — While 'Advanced Analytics and Insights' are mentioned, it is unclear if these analytics include security observability, real-time guardrails, or drift detection for the generated KB articles.

L6 · Security & Compliance (cross-cutting)⚠ not certain from listing

Not certain from the listing — No specific compliance certifications (e.g., SOC2, GDPR compliance for customer PII) or enterprise access controls are detailed in the public directory listing.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — Although users can build multiple 'AI agents', there is no explicit mention of a multi-agent marketplace or complex agent-to-agent delegation protocols that would introduce cascading ecosystem risks.

MAESTRO — the 7-layer agentic threat-modeling framework (Cloud Security Alliance / Ken Huang).