wiring-sbx-mcp-servers

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The documentation describes the functionality of the sbx mcp add --command flag, which allows for the execution of host-side processes. The instructions include security warnings regarding host-run servers, noting they operate outside of sandbox isolation with full host filesystem and network access.
  • [REMOTE_CODE_EXECUTION]: The skill provides instructions for registering remote MCP endpoints via the --url flag, facilitating connections to external servers.
  • [DATA_EXFILTRATION]: The content outlines best practices for credential management, including the use of sbx secret set to store OAuth client secrets in the host OS credential store rather than within individual sandboxes.
  • [INDIRECT_PROMPT_INJECTION]: The documentation describes the attack surface of the dynamic MCP gateway, which allows agents to discover and interact with external tool providers.
  • Ingestion points: Data enters the environment via registered MCP server endpoints (--url) or local packages (--local).
  • Boundary markers: The document details the use of Cedar policies (e.g., permit, forbid) to restrict tool invocation and registration.
  • Capability inventory: The gateway exposes tools like mcp-exec, mcp-add, and code-mode for dynamic tool execution.
  • Sanitization: Access is managed through identity URLs, OAuth scopes, and Cedar-enforced governance policies.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 04:43 PM
Security Audit — agent-trust-hub — wiring-sbx-mcp-servers