Reccopilot — agentic threat model
Reccopilot presents a moderate-to-high risk profile due to its handling of sensitive candidate PII and its integration with corporate ATS and communication channels, though its collaborative design suggests some human oversight.
OWASP AIVSS score rationale
| Autonomy of Action | 0.60 | |
| Goal-Driven Planning | 0.70 | |
| Self-Modification | 0.10 | |
| Dynamic Tool Use | 0.60 | |
| Persistent Memory | 0.50 | |
| Contextual Awareness | 0.60 | |
| Dynamic Identity | 0.30 | |
| Multi-Agent Interactions | 0.20 | |
| Non-Determinism | 0.50 | |
| Opacity & Reflexivity | 0.60 |
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 LLMs are unspecified. Primary threats include prompt injection via adversarial resumes designed to bypass AI-powered screening or manipulate decision support logic.
Not certain from the listing — The agent processes candidate resumes, job descriptions, and communication history. Threats include data exfiltration of sensitive PII and potential bias/poisoning in the assessment data.
Not certain from the listing — Orchestration details are omitted. Risks involve tool misuse, such as unauthorized job postings, automated spamming of candidates, or insecure API calls to external ATS platforms.
Not certain from the listing — Deployment infrastructure is not detailed. Risks include the compromise of API keys and credentials used to integrate with corporate workflow tools and job boards.
Not certain from the listing — No observability or guardrail mechanisms are described. Gaps here could lead to undetected drift in candidate evaluation criteria or silent failures in automated screening.
Not certain from the listing — Compliance frameworks are not mentioned. Given its role in hiring, the agent is subject to high-risk AI regulations (e.g., EU AI Act) regarding bias, transparency, and data privacy (GDPR).
Not certain from the listing — No explicit multi-agent ecosystem is described, but integration with external workflow tools introduces trust boundaries and potential cascading failures if those APIs are compromised.
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.