← UN Recruitment - AI Job Summary
UN Recruitment - AI Job Summary — agentic threat model
The UN Recruitment AI Job Summary agent is a low-risk, read-only information aggregator. Its primary security exposure is indirect prompt injection via manipulated job postings and the potential to serve as a phishing vector if compromised.
OWASP AIVSS score rationale
| Autonomy of Action | 0.10 | |
| Goal-Driven Planning | 0.10 | |
| Self-Modification | 0.00 | |
| Dynamic Tool Use | 0.10 | |
| Persistent Memory | 0.00 | |
| Contextual Awareness | 0.20 | |
| Dynamic Identity | 0.00 | |
| Multi-Agent Interactions | 0.00 | |
| Non-Determinism | 0.30 | |
| Opacity & Reflexivity | 0.20 |
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 uses a standard commercial LLM for text summarization. The primary threat is indirect prompt injection where a malicious job posting forces the model to output phishing links or system instructions.
Not certain from the listing — ingests external UN job descriptions via web scraping or APIs. Vulnerable to data poisoning if source websites are compromised or if the parser ingests untrusted user-generated job listings.
Not certain from the listing — likely uses a basic pipeline rather than a complex agentic framework. Risk of tool misuse is low as it only reads and summarizes data, but insecure parsing of scraped content remains a threat.
Not certain from the listing — hosted as a web application. Standard web hosting vulnerabilities apply, including potential Server-Side Request Forgery (SSRF) if the scraping engine is not properly sandboxed.
Not certain from the listing — no observability or evaluation guardrails are mentioned. Hallucinations in job requirements or salary details could pass through to users undetected.
Not certain from the listing — closed-source, free tool with no documented access controls, privacy policies, or compliance alignments.
Not certain from the listing — operates as a standalone vertical application with no indicated multi-agent collaboration or ecosystem integrations.
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.