AgentReadyHomeAgent Listing

← Kimi AI

Kimi AI — agentic threat model

7.7AIVSS 7.7 · High

Kimi AI presents a moderate agentic risk profile, primarily driven by its high-capacity data ingestion (200k characters) and real-time web search capabilities, which expose it to indirect prompt injection and data exfiltration threats, while its lack of autonomous execution limits direct physical or system-level impacts.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 6.5AARS uplift 1.22Factor sum 3.5/10Threat ×1.0Mitigation ×1.0
Autonomy of Action
0.30
Goal-Driven Planning
0.20
Self-Modification
0.10
Dynamic Tool Use
0.40
Persistent Memory
0.30
Contextual Awareness
0.70
Dynamic Identity
0.10
Multi-Agent Interactions
0.10
Non-Determinism
0.60
Opacity & Reflexivity
0.70

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✓ mapped

Uses Moonshot AI's proprietary LLM. Vulnerable to prompt injection, adversarial inputs (especially via long text/images), and model reprogramming.

L2 · Data Operations✓ mapped

Processes up to 200k characters of user-uploaded data (text, code, images, audio) and integrates real-time web data. Vulnerable to data exfiltration via prompt injection, and indirect prompt injection via web search or uploaded files.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — the orchestration framework for tool execution (web search, audio transcription, file parsing) is proprietary; vulnerabilities could lead to insecure tool calling or SSRF via web search.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — hosted as a closed-source cloud service by Moonshot AI; infrastructure security, sandboxing of file parsers, and network isolation are managed internally without public details.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — monitoring, guardrails, and abuse detection mechanisms are proprietary and not detailed in the public directory.

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

Not certain from the listing — compliance certifications (e.g., GDPR, local Chinese data regulations) and enterprise access controls are not specified in the basic directory listing.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — Kimi AI operates primarily as a standalone assistant; there is no explicit mention of multi-agent marketplace interactions or third-party agent integrations.

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