AgentReadyHomeAgent Listing

← Yevideo - AI Video and Image

Yevideo - AI Video and Image — agentic threat model

7.4AIVSS 7.4 · High

Yevideo is a low-autonomy multimodal generation platform with low agentic risk, primarily exposed to content abuse (such as deepfakes or policy-violating generations) and API-related vulnerabilities rather than autonomous decision-making failures.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 6.5AARS uplift 0.91Factor sum 2.6/10Threat ×1.0Mitigation ×1.0
Autonomy of Action
0.20
Goal-Driven Planning
0.20
Self-Modification
0.00
Dynamic Tool Use
0.30
Persistent Memory
0.20
Contextual Awareness
0.20
Dynamic Identity
0.00
Multi-Agent Interactions
0.00
Non-Determinism
0.80
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

The platform relies heavily on multimodal foundation models (text-to-video, image-to-video, etc.). These models are highly susceptible to adversarial prompt injections designed to bypass safety filters, potentially generating copyrighted, harmful, or deepfake content.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — The platform manages a 'Large Inspiration Library' and user-uploaded media assets. Gaps in data operations could lead to unauthorized access, data exfiltration of proprietary creative assets, or poisoning of the shared inspiration templates.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — Orchestration is focused on a 'One-Click Generate Similar' workflow that carries over generation settings. Vulnerabilities here include insecure parameter handling or prompt injection during the replication of creative directions.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — The platform provides an API and a unified web workspace. Infrastructure threats include unauthorized API access, lack of rate limiting leading to GPU resource exhaustion (DoS), and insecure storage of generated media assets.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — There is no mention of automated content moderation, output guardrails, or generation logging. A lack of observability could allow users to generate and export policy-violating content undetected.

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

Not certain from the listing — No compliance certifications (such as SOC2) or enterprise access controls (RBAC) are specified for the workspace or API, posing risks to corporate data governance.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — Although tagged as an 'AI Agents Platform', the description focuses on horizontal creative tools. There is no evidence of multi-agent coordination or third-party agent marketplaces, minimizing ecosystem-specific risks.

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