WeCP — agentic threat model
WeCP presents moderate agentic risk, primarily driven by its autonomy in conducting candidate evaluations and the high sensitivity of the PII and recruitment data it processes. The main threats involve prompt injection by candidates to game interviews and potential compliance violations under high-risk AI regulations.
OWASP AIVSS score rationale
| Autonomy of Action | 0.60 | |
| Goal-Driven Planning | 0.40 | |
| Self-Modification | 0.10 | |
| Dynamic Tool Use | 0.30 | |
| Persistent Memory | 0.40 | |
| Contextual Awareness | 0.50 | |
| Dynamic Identity | 0.10 | |
| Multi-Agent Interactions | 0.10 | |
| Non-Determinism | 0.60 | |
| 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 underlying foundation models are undisclosed. They are highly vulnerable to adversarial prompt injection by candidates attempting to bypass structured interview constraints, manipulate scoring, or extract system prompts.
Not certain from the listing — The platform processes sensitive candidate PII, resumes, and interview transcripts. Threats include data exfiltration of applicant databases and potential poisoning of the evaluation knowledge base if RAG is utilized.
Not certain from the listing — The orchestration framework managing the interview flow and real-time cheating detection is proprietary. Vulnerabilities could allow candidates to disrupt the interview state machine or bypass cheating detection mechanisms.
Not certain from the listing — Hosted deployment details are omitted. Standard cloud hosting threats apply, including unauthorized access to stored audio/video interview recordings and potential lack of sandboxing if candidates submit code during technical screenings.
The platform features real-time cheating detection and structured evaluations. A key threat is evaluation gaming, where candidates use sophisticated, undetected AI tools to bypass plagiarism and cheating detection, leading to compromised evaluation integrity.
Not certain from the listing — As an AI recruitment tool, this system falls under high-risk classifications in frameworks like the EU AI Act, requiring strict bias monitoring, transparency, and auditability. No specific compliance certifications (e.g., SOC 2) are detailed in the listing.
Not certain from the listing — The agent operates primarily as a standalone SaaS platform interacting with candidates and recruiters, with no explicit multi-agent or external ecosystem integrations described.
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.