eSkilled AI Course Creator — agentic threat model
The eSkilled AI Course Creator is a specialized content-generation agent with low operational autonomy, primarily posing risks related to content integrity, intellectual property, and compliance drift rather than active system compromise.
OWASP AIVSS score rationale
| Autonomy of Action | 0.20 | |
| Goal-Driven Planning | 0.30 | |
| Self-Modification | 0.10 | |
| Dynamic Tool Use | 0.20 | |
| Persistent Memory | 0.30 | |
| Contextual Awareness | 0.50 | |
| Dynamic Identity | 0.10 | |
| Multi-Agent Interactions | 0.10 | |
| Non-Determinism | 0.70 | |
| 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.
Not certain from the listing — relies on unspecified foundation models to generate text, quizzes, and images. Primary threats include model hallucination of educational facts, generation of biased/offensive training content, and prompt injection bypassing safety filters.
Not certain from the listing — likely utilizes internal educational databases, templates, or user-uploaded source materials to contextualize courses. Risks include data poisoning of course templates and potential exfiltration of proprietary corporate training data.
Not certain from the listing — orchestrates multi-step generation of lesson plans, quizzes, and SCORM packages. Vulnerabilities include insecure generation of SCORM-compliant XML/HTML payloads, which could lead to stored Cross-Site Scripting (XSS) in LMS environments.
Not certain from the listing — hosted as a closed-source SaaS platform. Standard web application infrastructure risks apply, including insecure storage of generated SCORM zip files and potential server-side resource exhaustion during heavy PDF/image generation.
Not certain from the listing — requires robust output validation to ensure generated quizzes and educational content align with accredited training standards. Lack of observability could lead to undetected drift in compliance-aligned content generation.
Not certain from the listing — must comply with educational data privacy standards (e.g., FERPA, GDPR) if student data is processed, though the tool appears focused on creator-side authoring. Access controls are needed to protect proprietary course designs.
Not certain from the listing — operates primarily as a standalone vertical SaaS tool. Minimal ecosystem risks unless integrated directly with external Learning Management Systems (LMS) via automated API publishing, which could introduce trust boundary issues.
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 — every score is re-derived by the same automated method as an agent's public evidence changes.