AgentReadyHomeAgent ListingPricing

← Winkwing

Winkwing — agentic threat model

6.4AIVSS 6.4 · Medium

Winkwing is a specialized monitoring and alerting agent with low agentic risk, primarily posing threats related to data scraping integrity, potential prompt injection via external housing listings, and the abuse of its email notification channel for phishing.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 5.5AARS uplift 0.9Factor sum 2.0/10Threat ×1.0Mitigation ×1.0
Autonomy of Action
0.40
Goal-Driven Planning
0.20
Self-Modification
0.00
Dynamic Tool Use
0.30
Persistent Memory
0.30
Contextual Awareness
0.30
Dynamic Identity
0.10
Multi-Agent Interactions
0.00
Non-Determinism
0.20
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.

L1 · Foundation Models⚠ not certain from listing

Not certain from the listing — likely uses LLMs for parsing unstructured housing listings. Threats include adversarial listings (indirect prompt injection embedded in housing descriptions) designed to bypass filters or trigger false alerts.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — ingests data from 750+ external websites. High risk of data poisoning if a housing site serves malicious or manipulated listings to skew the matching algorithm or inject malicious content.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — orchestrates scraping and email dispatch. Threats include insecure tool integration where the email dispatch system could be abused for spam or phishing if the orchestration layer is compromised.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — requires robust web scraping infrastructure and email servers. Threats include IP blocking, scraping bot detection bypasses, and insecure storage of user email addresses and search criteria.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — needs monitoring to ensure scraping accuracy and email delivery rates. Gaps could lead to silent failures where users miss listings, or drift in parsing accuracy over time.

L6 · Security & Compliance (cross-cutting)⚠ not certain from listing

Not certain from the listing — must comply with anti-scraping terms of service of 750+ sites, and data privacy laws (GDPR/CCPA) for storing user search criteria and emails.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — operates independently of other agent marketplaces. Minimal multi-agent risk unless interacting with external real estate agent APIs.

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.