AgentReadyHomeAgent ListingPricing

← Spot AI

Spot AI — agentic threat model

8.9AIVSS 8.9 · High

Spot AI presents a high-impact risk profile primarily due to its integration with physical security infrastructure (IP cameras) and real-time surveillance data, where compromise could lead to severe privacy violations and physical security breaches.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 8.4AARS uplift 0.5Factor sum 3.0/10Threat ×1.05Mitigation ×1.0
Autonomy of Action
0.30
Goal-Driven Planning
0.20
Self-Modification
0.00
Dynamic Tool Use
0.20
Persistent Memory
0.40
Contextual Awareness
0.70
Dynamic Identity
0.10
Multi-Agent Interactions
0.10
Non-Determinism
0.40
Opacity & Reflexivity
0.60

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 — relies on computer vision and video intelligence models which are highly susceptible to physical adversarial attacks (e.g., adversarial patches or clothing designed to evade detection) and model evasion.

L2 · Data Operations✓ mapped

Ingests, processes, and stores real-time video streams from local IP cameras. Key threats include unauthorized access to stored footage, data exfiltration of sensitive surveillance data, and potential tampering with video history.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — the orchestration layer managing video analytics pipelines and alerting logic is unspecified, but vulnerabilities here could allow attackers to suppress alerts or manipulate detection thresholds.

L4 · Deployment & Infrastructure✓ mapped

Deployed as a hybrid cloud video platform connecting to local IP cameras. This introduces risks of edge gateway compromise, lateral movement from the cloud platform into local OT/IT networks, and unauthorized access to cloud dashboards.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — lacks details on how model drift, false positive rates, or camera tampering (e.g., lens covering) are monitored and validated to prevent blind spots.

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

Not certain from the listing — surveillance platforms require strict role-based access control (RBAC) and compliance with privacy regulations (GDPR/CCPA) regarding facial recognition and public recording, which are not detailed here.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — potential integrations with external physical security systems (e.g., access control, alarms) could lead to cascading failures or unauthorized physical access if the AI triggers false positives.

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.