schedx — agentic threat model
SchedX exhibits a moderate-to-high risk profile due to its public-facing nature and direct integration with critical business systems like CRMs and calendars. A compromise could lead to unauthorized data exfiltration of customer leads or manipulation of sales pipelines.
OWASP AIVSS score rationale
| Autonomy of Action | 0.80 | |
| Goal-Driven Planning | 0.60 | |
| Self-Modification | 0.10 | |
| Dynamic Tool Use | 0.70 | |
| Persistent Memory | 0.60 | |
| Contextual Awareness | 0.60 | |
| Dynamic Identity | 0.20 | |
| Multi-Agent Interactions | 0.20 | |
| Non-Determinism | 0.70 | |
| Opacity & Reflexivity | 0.70 |
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 — The underlying foundation models are not disclosed. The agent is susceptible to prompt injection, adversarial input from website visitors, and potential model reprogramming to output misaligned or brand-damaging content.
The agent trains deeply on product data and integrates with CRMs. This introduces risks of knowledge-base poisoning if product documentation is manipulated, and data exfiltration of sensitive CRM lead data via prompt injection.
The agent orchestrates qualification, discovery, and scheduling. Insecure tool integration with calendars and CRMs could allow attackers to abuse tool-calling capabilities to modify records or book unauthorized slots.
Not certain from the listing — The hosting environment, network isolation, and secrets management for CRM API keys are not detailed, presenting potential risks of credential theft or container compromise.
Not certain from the listing — There is no mention of real-time guardrails, input/output filtering, or drift detection to monitor conversational anomalies or malicious injection attempts.
Not certain from the listing — No compliance certifications (e.g., SOC2, GDPR) or explicit access control policies for CRM integrations are specified in the directory listing.
Not certain from the listing — While it routes leads to human reps, there is no explicit multi-agent orchestration or marketplace interaction described that would introduce cascading agent-to-agent trust risks.
MAESTRO — the 7-layer agentic threat-modeling framework (Cloud Security Alliance / Ken Huang).