Plottie — agentic threat model
Plottie presents a low-to-moderate agentic risk profile, primarily acting as a human-in-the-loop assistant for scientific figure generation. The main security concerns stem from potential injection attacks manipulating the multi-LLM backends and vulnerabilities in the file export (PDF/SVG) and rendering pipelines.
OWASP AIVSS score rationale
| Autonomy of Action | 0.20 | |
| Goal-Driven Planning | 0.30 | |
| Self-Modification | 0.00 | |
| Dynamic Tool Use | 0.30 | |
| Persistent Memory | 0.20 | |
| Contextual Awareness | 0.40 | |
| Dynamic Identity | 0.00 | |
| Multi-Agent Interactions | 0.00 | |
| 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.
Utilizes third-party foundation models (Claude, Gemini, GPT) to interpret natural language and generate plot structures. Threats include prompt injection to bypass safety filters, model misalignment, and adversarial inputs designed to generate misleading or fraudulent scientific figures.
Maintains a curated database of 100,000+ scientific plots indexed via Typesense. Threats include database poisoning with fraudulent or copyrighted papers, search manipulation, and unauthorized exfiltration of user-curated collections.
Not certain from the listing — the specific orchestration framework is not disclosed. Threats include insecure tool integration where LLM-generated code or layout instructions are parsed by the Excalidraw/Konva canvas, potentially leading to cross-site scripting (XSS) or canvas manipulation.
Not certain from the listing — hosting and infrastructure details are omitted. Threats include server-side request forgery (SSRF) or remote code execution (RCE) during the server-side rendering and export of PDF, SVG, and PNG formats.
Not certain from the listing — there is no mention of output validation, guardrails, or logging. Threats include a lack of visibility into malicious prompt injections or generated figures containing offensive or scientifically fraudulent content.
Not certain from the listing — authentication, authorization, and compliance standards are not detailed. Threats include unauthorized access to user accounts and lack of alignment with academic integrity or data privacy regulations.
Operates as a standalone vertical tool with no multi-agent or marketplace interactions described. Ecosystem threats are minimal, restricted primarily to upstream supply chain risks from the third-party LLM providers.
MAESTRO — the 7-layer agentic threat-modeling framework (Cloud Security Alliance / Ken Huang).
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology. Are you the vendor? Factual corrections are free.