# Security Model SignTx employs a defense-in-depth security architecture, designed to address potential attack vectors at multiple levels: * **Key Isolation:** Private keys are stored in secure enclaves and never exposed to AI agents or external services. * **AI Operation Boundaries:** AI agents operate within sandboxed environments with strict access controls. * **Transaction Validation:** All AI-generated transaction payloads undergo integrity checks and user approval before signing. * **Contract Risk Analysis:** Automated scoring of smart contracts based on known vulnerabilities, code patterns, and onchain history. * **Encrypted Communications:** End-to-end encryption for all platform communications. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://signtx.gitbook.io/signtx/security-model.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.