AgentReadyHomeAgent Listing

← BlockSurvey

BlockSurvey — agentic threat model

8.2AIVSS 8.2 · High

BlockSurvey's AI agent presents a moderate risk profile primarily centered on data privacy and indirect prompt injection, as it processes sensitive HR and survey data from multiple external platforms without explicit sandboxing or advanced autonomous capabilities.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 7.5AARS uplift 0.65Factor sum 2.6/10Threat ×1.0Mitigation ×1.0
Autonomy of Action
0.30
Goal-Driven Planning
0.20
Self-Modification
0.00
Dynamic Tool Use
0.30
Persistent Memory
0.40
Contextual Awareness
0.50
Dynamic Identity
0.00
Multi-Agent Interactions
0.00
Non-Determinism
0.50
Opacity & Reflexivity
0.40

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 specific foundation models used for generating survey questions and analyzing data are not disclosed. Standard risks include prompt injection to bypass survey generation constraints and potential model hallucinations during data analysis.

L2 · Data Operations✓ mapped

The agent ingests and processes survey data from multiple external sources (Google Forms, Typeform, etc.). This introduces significant risks of data poisoning (malicious survey responses designed to skew AI insights) and unauthorized exfiltration of sensitive HR or personal data contained within the surveys.

L3 · Agent Frameworks✓ mapped

The agent framework orchestrates a chat assistant to query survey data. This creates a vector for indirect prompt injection, where malicious data inside an uploaded survey could hijack the chat assistant's instructions to exfiltrate data or mislead the user.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — The hosting environment, API integration security, and sandboxing mechanisms for processing uploaded files (CSV, Excel, etc.) are not detailed in the public directory listing.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — There is no mention of continuous evaluation, drift detection, or guardrails to ensure the AI-generated survey questions remain unbiased and the analysis remains accurate over time.

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

Not certain from the listing — While the tool is used for Human Resources and research (which heavily involve PII and compliance frameworks like GDPR), the listing does not specify concrete compliance certifications, encryption standards, or access control policies.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — The agent operates primarily as a single-agent utility for survey generation and analysis, with no indicated multi-agent collaboration or marketplace ecosystem risks.

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