AgentReadyHomeAgent Listing

← MiniWork AI

MiniWork AI — agentic threat model

5.5AIVSS 5.5 · Medium

MiniWork AI is a low-risk, content-focused AI assistant primarily used for summarization and writing, presenting minimal agentic risk due to its lack of autonomy, planning, or tool-execution capabilities.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 4.8AARS uplift 0.73Factor sum 1.4/10Threat ×1.0Mitigation ×1.0
Autonomy of Action
0.10
Goal-Driven Planning
0.10
Self-Modification
0.00
Dynamic Tool Use
0.20
Persistent Memory
0.10
Contextual Awareness
0.20
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.

L1 · Foundation Models⚠ not certain from listing

Not certain from the listing — likely relies on third-party commercial LLMs for smart chat and summarization. Vulnerable to prompt injection, adversarial inputs, and model alignment issues.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — processes user-provided video links or files for summarization. Vulnerable to data exfiltration via malicious video transcripts or injection of malicious content in the source videos.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — orchestration appears minimal, likely a simple pipeline for chat, summarization, and mind-map generation. Vulnerable to insecure tool integration if the video parser is exploited.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — hosted as a closed-source web application. Vulnerable to standard web application threats, SSRF (if fetching video URLs directly), and infrastructure compromise.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — no public details on guardrails, output filtering, or logging. Vulnerable to generating inappropriate content or failing to detect prompt injections.

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

Not certain from the listing — closed-source, paid tool with no explicit security certifications or compliance frameworks mentioned. Vulnerable to data privacy violations if user inputs/videos are stored insecurely.

L7 · Agent Ecosystem✓ mapped

No multi-agent or marketplace interactions are described in the listing; it operates as a standalone tool suite, minimizing ecosystem-level cascading risks.

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