AgentReadyHomeAgent Listing

← Bookshelf

Bookshelf — agentic threat model

5.9AIVSS 5.9 · Medium

Bookshelf is a low-risk, content-focused agent primarily serving as a book summarization and file delivery platform, presenting minimal agentic risk but potential exposure to content poisoning and file-based malware delivery if compromised.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 5.5AARS uplift 0.43Factor sum 1.0/10Threat ×0.95Mitigation ×1.0
Autonomy of Action
0.10
Goal-Driven Planning
0.00
Self-Modification
0.00
Dynamic Tool Use
0.10
Persistent Memory
0.10
Contextual Awareness
0.20
Dynamic Identity
0.00
Multi-Agent Interactions
0.00
Non-Determinism
0.30
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 utilizes standard LLMs for text summarization and text-to-speech models for audio generation. Primary threats include prompt injection to alter summary outputs or generate inappropriate content.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — relies on an ingestion pipeline for books. Threats include data poisoning of the source text corpus and intellectual property/copyright provenance issues.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — likely uses a basic linear pipeline rather than an active agentic framework. Risks of tool misuse are low and restricted to document/audio generation utilities.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — hosted on bookshelf.ai. Standard web infrastructure risks apply, including potential container compromise or insecure storage of generated PDF/EPUB/audio files.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — no observability or guardrail mechanisms are mentioned. Lack of monitoring could allow hallucinated or biased summaries to bypass detection.

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

Not certain from the listing — closed-source freemium model. Compliance risks are primarily centered around copyright regulations and user data protection (GDPR/CCPA) for registered accounts.

L7 · Agent Ecosystem✓ mapped

The agent operates as a standalone vertical application with no multi-agent orchestration or marketplace integration described, making ecosystem-level threats negligible.

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