AgentReadyHomeAgent Listing

← AIDirHub

AIDirHub — agentic threat model

4.5AIVSS 4.5 · Medium

AIDirHub is a curated directory of AI tools with negligible agentic risk, as it lacks autonomous execution, planning, or tool-calling capabilities. The primary security risks are traditional web vulnerabilities, such as malicious tool submissions or directory defacement.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 4.3AARS uplift 0.15Factor sum 0.3/10Threat ×0.9Mitigation ×1.0
Autonomy of Action
0.00
Goal-Driven Planning
0.00
Self-Modification
0.00
Dynamic Tool Use
0.00
Persistent Memory
0.00
Contextual Awareness
0.10
Dynamic Identity
0.00
Multi-Agent Interactions
0.00
Non-Determinism
0.10
Opacity & Reflexivity
0.10

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 — the directory may use a simple embedding model or basic keyword search, but no specific foundation model is mentioned. If an LLM is used for search parsing, it could be vulnerable to prompt injection.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — the data operations consist of storing and querying a curated list of 325+ AI tools. The primary threat is data poisoning if the submission pipeline is compromised to inject malicious links.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — there is no evidence of an active agent framework or orchestration layer; the system functions as a standard web directory rather than an autonomous agent.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — hosting and deployment infrastructure details are not provided. Standard web hosting vulnerabilities, such as server misconfiguration or lack of DDoS protection, represent the main threats.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — no evaluation, logging, or observability guardrails are mentioned. The system relies on manual human review ('hand-checked') to filter out malicious or low-quality submissions.

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

Not certain from the listing — no authentication or compliance frameworks are mentioned. Security relies entirely on the administrator's manual vetting process for tool submissions.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — the platform does not participate in an active agent ecosystem or multi-agent marketplace, serving only as a static directory pointing to external tools.

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