Surva.ai — agentic threat model
Surva.ai presents a moderate-to-high risk profile due to its integration with sensitive third-party services like Stripe, Gmail, and Outlook, where compromised agent logic could lead to unauthorized subscription cancellations or data exfiltration.
OWASP AIVSS score rationale
| Autonomy of Action | 0.40 | |
| Goal-Driven Planning | 0.30 | |
| Self-Modification | 0.10 | |
| Dynamic Tool Use | 0.60 | |
| Persistent Memory | 0.50 | |
| Contextual Awareness | 0.50 | |
| Dynamic Identity | 0.20 | |
| Multi-Agent Interactions | 0.10 | |
| Non-Determinism | 0.50 | |
| Opacity & Reflexivity | 0.40 |
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 — The specific foundation models used for survey generation and feedback analysis are not disclosed, leaving threats like model-specific prompt injection or data leakage unquantified.
The agent ingests customer feedback, survey responses, and testimonial data, and integrates with Stripe, Gmail, and Outlook, presenting risks of data exfiltration or injection of malicious feedback to manipulate analytics.
Not certain from the listing — The underlying orchestration framework is not specified, but the integration with Stripe and email tools poses risks of insecure tool execution or prompt injection manipulating cancellation flows.
Not certain from the listing — While the project is open-source, the deployment environment (SaaS vs. self-hosted) and sandboxing controls for executing integrations are not detailed.
Not certain from the listing — Real-time analytics are mentioned, but there is no indication of LLM-specific guardrails, input filtering, or drift detection mechanisms.
Not certain from the listing — Although handling Stripe (payment/subscription) and email (Gmail/Outlook) data implies strict compliance needs, no specific security certifications or access control policies are detailed.
The listing does not indicate any multi-agent orchestration or marketplace ecosystem interactions, suggesting a single-agent architecture with low ecosystem risk.
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.