bim-visual-programming-automation

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external project data formats like Excel, CSV, and JSON to automate BIM tasks, creating a surface for indirect prompt injection.
  • Ingestion points: Data provided via user project files, file paths, or parameters as referenced in the instructions.
  • Boundary markers: Absent; there are no defined delimiters or instructions to treat ingested file content purely as data.
  • Capability inventory: The skill provides Python code to modify BIM element parameters, batch copy elements, and generate schedules.
  • Sanitization: Absent; the skill lacks specific validation or sanitization of the contents of external files before model modification.
  • [COMMAND_EXECUTION]: The skill includes Python scripts that use the clr (Common Language Runtime) module to interact with the Revit API. These scripts can perform broad model-level operations, including database transactions and batch element modifications, which require careful handling of user inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 11:15 PM