HockeyStack — agentic threat model
HockeyStack presents a high-risk profile due to its multi-agent architecture (Odin and Nova) automating sales workflows and analyzing sensitive B2B customer journey data, where compromise could lead to unauthorized CRM actions and data exfiltration.
OWASP AIVSS score rationale
| Autonomy of Action | 0.70 | |
| Goal-Driven Planning | 0.60 | |
| Self-Modification | 0.10 | |
| Dynamic Tool Use | 0.70 | |
| Persistent Memory | 0.80 | |
| Contextual Awareness | 0.80 | |
| Dynamic Identity | 0.40 | |
| Multi-Agent Interactions | 0.60 | |
| Non-Determinism | 0.50 | |
| 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 — likely utilizes commercial LLMs for Odin and Nova. Threats include prompt injection leading to unauthorized report generation or workflow execution, and potential data leakage via model APIs.
Not certain from the listing — ingests large volumes of B2B customer journey and CRM data. Threats include data poisoning of the analytics database, unauthorized data exfiltration of sensitive customer PII, and lineage gaps in tracking customer behavior.
Orchestrates Odin (analyst) and Nova (workflow automation). Threats include insecure tool integration with CRMs/marketing platforms, allowing prompt injection to trigger unintended sales workflows or API calls.
Not certain from the listing — hosted SaaS platform. Threats include container compromise, unauthorized access to API keys for integrated CRM/marketing tools, and lack of sandboxing for data processing.
Not certain from the listing — no mention of guardrails or monitoring for Odin/Nova's outputs. Threats include drift in automated sales workflows and undetected prompt injection attacks.
Not certain from the listing — closed source, pricing on contact. No explicit mention of SOC2, GDPR, or role-based access control (RBAC) for agent actions. Threats include unauthorized privilege escalation within the platform.
Features multiple agents (Odin and Nova) working within the same platform. Threats include cascading failures if Odin's analytical output poisons Nova's automated workflow triggers, or unauthorized cross-agent trust exploitation.
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. Are you the vendor? Factual corrections are free.