AgentReadyHomeAgent Listing

← Claygent

Claygent — agentic threat model

8.1AIVSS 8.1 · High

Claygent presents a moderate-to-high risk profile primarily driven by its autonomous web-scraping capabilities, which expose it to indirect prompt injection and SSRF vulnerabilities when processing untrusted third-party web content.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 7.5AARS uplift 1.0Factor sum 4.0/10Threat ×1.0Mitigation ×0.95
Autonomy of Action
0.70
Goal-Driven Planning
0.60
Self-Modification
0.10
Dynamic Tool Use
0.50
Persistent Memory
0.20
Contextual Awareness
0.50
Dynamic Identity
0.20
Multi-Agent Interactions
0.10
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.

L1 · Foundation Models⚠ not certain from listing

Not certain from the listing — The underlying LLMs are unspecified. A key threat is indirect prompt injection, where malicious instructions embedded in scraped websites hijack the model's behavior during research tasks.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — The agent processes scraped web data and user-provided prospecting lists. Threats include data poisoning from malicious websites and potential exfiltration of sensitive CRM or business intelligence data.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — The orchestration framework is proprietary. Threats include insecure tool integration where the web-scraping tool is manipulated into performing unintended actions or executing malicious scripts.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — Hosted on Clay's infrastructure. The primary threat is Server-Side Request Forgery (SSRF) if the agent's web-scraping mechanism can be coerced into scanning internal network resources.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — Observability features are not detailed. Gaps in logging could allow stealthy indirect prompt injections or data exfiltration attempts to go unnoticed.

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

Not certain from the listing — Compliance controls are not specified. Scraping personal data of individuals for sales prospecting poses significant GDPR, CCPA, and data privacy compliance risks.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — The agent integrates with the broader Clay ecosystem and external CRMs. Threats include cascading data corruption or unauthorized data modification in connected downstream systems like Salesforce or HubSpot.

MAESTRO — the 7-layer agentic threat-modeling framework (Cloud Security Alliance / Ken Huang).