AgentReadyHomeAgent Listing

← Fabi.ai

Fabi.ai — agentic threat model

9.1AIVSS 9.1 · Critical

Fabi.ai presents a moderate-to-high risk profile primarily due to its direct integration with enterprise data sources, where prompt injection could lead to unauthorized data extraction or SQL execution.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 8.5AARS uplift 0.55Factor sum 3.7/10Threat ×1.0Mitigation ×1.0
Autonomy of Action
0.40
Goal-Driven Planning
0.50
Self-Modification
0.10
Dynamic Tool Use
0.70
Persistent Memory
0.30
Contextual Awareness
0.50
Dynamic Identity
0.20
Multi-Agent Interactions
0.10
Non-Determinism
0.50
Opacity & Reflexivity
0.40

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 foundation models to translate natural language into SQL/code. Key threats include prompt injection that bypasses system instructions to access unauthorized data.

L2 · Data Operations✓ mapped

Utilizes direct data source connectors to query database schemas and records. This creates a high risk of data exfiltration and exposure of sensitive business intelligence if the agent is compromised.

L3 · Agent Frameworks✓ mapped

Orchestrates workflows and executes queries against connected databases. Vulnerabilities include insecure tool integration, where the agent might execute destructive write queries or be manipulated into SQL injection.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — likely hosted as a closed-source SaaS. Main threats involve the secure storage of database credentials/secrets and potential lateral movement if the hosting environment is breached.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — requires robust logging of executed queries and LLM inputs. Gaps here could lead to undetected data harvesting or silent prompt injection attacks.

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

Not certain from the listing — requires strict tenant isolation and credential encryption. Lack of fine-grained access controls could allow users to query data sources they are not authorized to see.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — operates primarily as a standalone data assistant. Ecosystem risks are minimal unless it integrates with external third-party agent marketplaces.

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