AgentReadyHomeAgent Listing

← doforai

doforai — agentic threat model

5.2AIVSS 5.2 · Medium

Doforai is a curated AI directory with minimal agentic capabilities, presenting low direct security risks. The primary threat involves data integrity, where a compromise could lead to the promotion of malicious or unvetted tools to users.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 5.0AARS uplift 0.23Factor sum 0.5/10Threat ×0.9Mitigation ×1.0
Autonomy of Action
0.00
Goal-Driven Planning
0.00
Self-Modification
0.00
Dynamic Tool Use
0.10
Persistent Memory
0.00
Contextual Awareness
0.10
Dynamic Identity
0.00
Multi-Agent Interactions
0.00
Non-Determinism
0.20
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 listing does not specify if an LLM is used for search/curation or if it is a traditional database. If an LLM is used, threats include prompt injection to manipulate search results or bypass curation.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — The directory relies on a curated dataset of AI tools. Threats include data poisoning of the directory database or curation pipeline, leading to malicious tools being marked as verified.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — There is no indication of an active agent framework (planning, memory, tool calling) being used; it behaves primarily as a standard web directory.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — Standard web hosting threats apply, such as compromise of the web server, database, or DNS to redirect users to malicious sites.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — No mention of evaluation or observability frameworks for monitoring search/curation quality or detecting anomalous queries.

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

Not certain from the listing — No details on authentication, access controls for curators, or compliance standards (e.g., GDPR for user accounts) are provided.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — The platform lists other AI tools/agents but does not interact with them programmatically as a multi-agent ecosystem.

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