Atomic Mail — agentic threat model
Atomic Mail is a traditional secure email service with zero described agentic capabilities, presenting minimal AI-specific risk but carrying high traditional data sensitivity due to its target user base of journalists and activists.
OWASP AIVSS score rationale
| Autonomy of Action | 0.00 | |
| Goal-Driven Planning | 0.00 | |
| Self-Modification | 0.00 | |
| Dynamic Tool Use | 0.00 | |
| Persistent Memory | 0.00 | |
| Contextual Awareness | 0.00 | |
| Dynamic Identity | 0.00 | |
| Multi-Agent Interactions | 0.00 | |
| Non-Determinism | 0.00 | |
| Opacity & Reflexivity | 0.00 |
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.
Not certain from the listing — Atomic Mail is described as a secure email service and does not mention using foundation models or LLMs.
Not certain from the listing — The service uses zero-access encrypted storage for emails, but there is no mention of AI data operations, vector databases, or RAG pipelines.
Not certain from the listing — No agent orchestration framework, planning, or tool-calling capabilities are described for this application.
Not certain from the listing — While it is an open-source email service, specific hosting, sandboxing, or infrastructure deployment details are not provided.
Not certain from the listing — No AI-specific evaluation, guardrails, or LLM observability tools are mentioned.
The service implements strong traditional security controls including end-to-end encryption, zero-access storage, and disposable aliases to protect user identity and data privacy.
Not certain from the listing — There are no multi-agent interactions or agent marketplace integrations described.
MAESTRO — the 7-layer agentic threat-modeling framework (Cloud Security Alliance / Ken Huang).