claroty-asset-inventory

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script (mcp-servers/claroty-mcp/claroty_mcp_server.py) to initiate the MCP server. This is the intended execution model for providing the asset management functionality.
  • [DATA_EXFILTRATION]: The skill interacts with external APIs (Claroty, Nautobot, NetBox) to retrieve and update asset data. Credential management follows standard practices by utilizing environment variables (CLAROTY_API_TOKEN) rather than hardcoding sensitive information.
  • [PROMPT_INJECTION]: No evidence was found of instructions attempting to bypass safety guardrails or override agent behavior. The instructions are focused on operational tasks and integration logic.
  • [SAFE]: The skill includes defensive design patterns such as mandatory Change Request (CR) validation for write operations via ServiceNow integration and an audit trail (GAIT) for all tool invocations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 04:29 PM
Security Audit — agent-trust-hub — claroty-asset-inventory