AgentReadyHomeAgent Listing

← BookPlotter

BookPlotter — agentic threat model

4.3AIVSS 4.3 · Medium

BookPlotter is a low-risk, consumer-focused reading assistant with minimal agentic capabilities, primarily vulnerable to prompt injection and basic web application threats rather than systemic agentic failures.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 3.5AARS uplift 0.82Factor sum 1.4/10Threat ×0.9Mitigation ×1.0
Autonomy of Action
0.10
Goal-Driven Planning
0.10
Self-Modification
0.00
Dynamic Tool Use
0.10
Persistent Memory
0.30
Contextual Awareness
0.20
Dynamic Identity
0.00
Multi-Agent Interactions
0.00
Non-Determinism
0.40
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 standard commercial LLMs for summarization and quiz generation. Vulnerable to prompt injection (e.g., forcing it to generate inappropriate quizzes or bypass paywalls) and misaligned outputs.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — relies on a database of books, user reading lists, and potentially RAG for book content. Vulnerable to data poisoning if users can upload custom books/texts, or unauthorized access to user reading history.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — likely a simple orchestrator rather than a complex agent framework. Vulnerable to insecure state management of user progress and reading lists.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — hosted as a standard web/mobile app backend. Standard web vulnerabilities (OWASP Top 10) apply, with low risk of lateral movement due to isolated containerization.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — no mention of guardrails or LLM evaluation frameworks. Vulnerable to drift in summary quality or generation of hallucinated book facts.

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

Not certain from the listing — likely standard OAuth/email login for freemium tracking. Lacks explicit compliance certifications (e.g., SOC2, GDPR) mentioned in the directory.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — operates as a standalone vertical application with no multi-agent or marketplace integrations. Low ecosystem risk.

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