Recruit CRM — agentic threat model
Recruit CRM presents a moderate-to-high risk profile primarily due to its handling of sensitive candidate PII and recruitment data across a global user base. The lack of transparency regarding its closed-source AI matching models and data processing pipelines necessitates cautious deployment and strict external access controls.
OWASP AIVSS score rationale
| Autonomy of Action | 0.40 | |
| Goal-Driven Planning | 0.30 | |
| Self-Modification | 0.00 | |
| Dynamic Tool Use | 0.40 | |
| Persistent Memory | 0.80 | |
| Contextual Awareness | 0.50 | |
| Dynamic Identity | 0.20 | |
| Multi-Agent Interactions | 0.10 | |
| Non-Determinism | 0.40 | |
| Opacity & Reflexivity | 0.50 |
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 specific LLMs or foundation models used for parsing or matching are not disclosed. Potential threats include prompt injection leading to biased candidate screening or data leakage.
Not certain from the listing — While it manages extensive candidate PII and CRM data, the underlying vector database or RAG architecture is unspecified. Threats include data poisoning of candidate profiles and unauthorized data exfiltration.
Not certain from the listing — The orchestration framework for the AI agents is closed-source and unspecified. Threats include insecure tool integration with email/calendar systems and manipulation of automated recruitment workflows.
Not certain from the listing — The hosting environment (likely public cloud) and sandboxing mechanisms are not detailed. Threats include container compromise or unauthorized access to the multi-tenant database.
Not certain from the listing — No details are provided regarding bias monitoring, drift detection, or audit logging for AI-driven hiring decisions. Threats include undetected algorithmic bias and lack of auditability.
Not certain from the listing — Although used globally, specific compliance certifications (e.g., GDPR, SOC2) are not explicitly detailed in the listing. Threats include regulatory non-compliance regarding automated decision-making.
Not certain from the listing — There is no explicit mention of multi-agent orchestration or third-party agent marketplace integrations. Threats are limited to standard API integrations with external job boards and email providers.
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.