arcgis-pro-automation

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a restrictive path boundary using the ARCGIS_MCP_ALLOWED_ROOTS configuration variable. This 'PathGuard' mechanism ensures that all file-based read and write operations are confined to specific, user-approved directories, preventing unauthorized access to the broader file system.
  • [SAFE]: Mutating operations—including data deletion, attribute calculation, and project modifications—are protected by mandatory confirmation gates. The agent is instructed to only set the confirm=true flag when the user has provided explicit authorization for a specific target and operation, reducing the risk of accidental or unauthorized data loss.
  • [COMMAND_EXECUTION]: The skill facilitates local geoprocessing via the arcgis-mcp-bridge tool. This involves executing ArcPy commands within a dedicated worker process. For tools like calculate_field that support Python expressions, the skill provides specific security guidance to inspect input expressions for untrusted code or environment leakage before execution.
  • [EXTERNAL_DOWNLOADS]: The skill references the arcgis-mcp-bridge package. This is a vendor-owned resource provided by the skill author ('muend') and serves as the primary execution backend for the automation workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 12:19 PM
Security Audit — agent-trust-hub — arcgis-pro-automation