AgentReadyHomeAgent Listing

← AskCory.ai

AskCory.ai — agentic threat model

6.9AIVSS 6.9 · Medium

AskCory.ai presents a low-to-moderate agentic risk profile, acting primarily as a content and strategy generator with human-in-the-loop execution. The primary security concerns center on data privacy for agency clients and the potential for generating brand-damaging or misaligned marketing content.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 5.7AARS uplift 1.25Factor sum 2.9/10Threat ×1.0Mitigation ×1.0
Autonomy of Action
0.20
Goal-Driven Planning
0.40
Self-Modification
0.10
Dynamic Tool Use
0.20
Persistent Memory
0.30
Contextual Awareness
0.40
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.

L1 · Foundation Models⚠ not certain from listing

Not certain from the listing — likely relies on commercial LLMs (e.g., OpenAI, Anthropic) for strategy and content generation. Vulnerable to prompt injection, model drift, and generation of misaligned or copyrighted marketing content.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — processes user business profiles and campaign requirements. Risks include data leakage of proprietary marketing strategies or client details, especially in white-label agency setups.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — orchestrates strategy and KPI generation. Vulnerable to insecure prompt templates or framework-level manipulation if user inputs can bypass the 'no prompting' UI.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — hosted as a closed-source SaaS platform. Standard web application security risks apply, including potential exposure of tenant data in multi-tenant agency environments.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — no mention of real-time monitoring, guardrails, or output validation to prevent toxic, biased, or brand-damaging content generation.

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

Not certain from the listing — lacks explicit mention of compliance certifications (e.g., SOC 2, GDPR) or robust access controls for agency white-labeling.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — operates primarily as a standalone SaaS assistant. No evidence of multi-agent marketplace interactions or external agent integrations.

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