11.ai — agentic threat model
11.ai presents a high-risk profile due to its integration with critical enterprise tools (Slack, Notion, Linear) via the Model Context Protocol (MCP) and its ability to execute sequential actions, compounded by its alpha-stage maturity.
OWASP AIVSS score rationale
| Autonomy of Action | 0.70 | |
| Goal-Driven Planning | 0.80 | |
| Self-Modification | 0.10 | |
| Dynamic Tool Use | 0.80 | |
| Persistent Memory | 0.50 | |
| Contextual Awareness | 0.80 | |
| Dynamic Identity | 0.40 | |
| Multi-Agent Interactions | 0.30 | |
| Non-Determinism | 0.70 | |
| Opacity & Reflexivity | 0.60 |
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 — uses multimodal/voice-first models for natural voice/text interaction, but specific foundation models are not disclosed. Vulnerable to prompt injection via voice (vishing/audio injection) and standard adversarial inputs.
Integrates with Slack, Linear, Perplexity, and Notion, creating risks of data exfiltration, unauthorized RAG retrieval, and knowledge-base poisoning from compromised connected workspaces.
Uses Model Context Protocol (MCP) for tool orchestration and sequential action planning. Risks include insecure tool integration, tool misuse (e.g., unauthorized Slack posting or Notion modification), and MCP-specific protocol vulnerabilities.
Not certain from the listing — deployment infrastructure, sandboxing of MCP servers, and secrets management for connected integrations (Slack, Notion) are not detailed in the public listing.
Not certain from the listing — being in alpha stage suggests observability, guardrails, and logging may be immature or not fully hardened against adversarial exploitation.
Not certain from the listing — claims to connect 'securely' to tools, but specific authentication mechanisms (OAuth, API keys), authorization policies, and compliance alignments are not disclosed.
Interacts with an ecosystem of tools (Slack, Linear, Notion) via MCP. Risks include cascading failures across connected platforms and trust abuse if a connected workspace or MCP server is compromised.
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.