AgentReadyHomeAgent Listing

← SkillMap: AI Skill manager

SkillMap: AI Skill manager — agentic threat model

9.1AIVSS 9.1 · Critical

SkillMap acts as a centralized control plane for distributing AI skills across developer IDEs, presenting a high-impact supply chain risk where compromise could allow malicious code propagation to multiple developer environments.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 8.8AARS uplift 0.26Factor sum 2.0/10Threat ×1.1Mitigation ×1.0
Autonomy of Action
0.30
Goal-Driven Planning
0.10
Self-Modification
0.10
Dynamic Tool Use
0.40
Persistent Memory
0.20
Contextual Awareness
0.20
Dynamic Identity
0.20
Multi-Agent Interactions
0.10
Non-Determinism
0.20
Opacity & Reflexivity
0.20

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 which foundation models are used to power the SkillMap search or management capabilities.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — The listing mentions searching and version tracking of AI skills, but does not detail the underlying database, vector store, or data lineage mechanisms.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — While it acts as a control plane for 'AI skills,' the internal orchestration framework, memory, and tool-calling mechanisms of SkillMap itself are not disclosed.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — The agent distributes skills across IDEs and centralizes updates, but the hosting environment, sandboxing of installed skills, and secrets management are not described.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — There is no mention of evaluation metrics, guardrails, or observability logging for the skills being deployed or the control plane itself.

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

Not certain from the listing — The listing does not detail authentication, authorization, or compliance certifications for managing and distributing code/skills across enterprise IDEs.

L7 · Agent Ecosystem✓ mapped

SkillMap acts as a central repository and control plane for 'AI skills' across multiple IDEs. This introduces significant supply chain risks where a compromised skill could be distributed to multiple developer environments, leading to cascading trust abuse.

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