autodesk-revit

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the membrane CLI tool to perform operations. These commands are standard for the integration's functionality and involve authentication, action discovery, and execution within the vendor's ecosystem.
  • [EXTERNAL_DOWNLOADS]: The skill directs the installation of the @membranehq/cli package via npm. This is an official tool from the skill's author used to facilitate the integration.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface where data from Autodesk Revit is ingested into the agent context via action outputs. While this represents a theoretical attack vector common to all data-processing skills, no specific malicious patterns or lack of sanitization were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 08:46 PM