ifcos-errors-performance

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides documentation on using subprocess isolation via subprocess.run to execute Python code. This is a standard and recommended practice for IfcOpenShell to manage peak memory usage and ensure C++ allocated resources are fully reclaimed by the operating system after processing very large models.
  • [PROMPT_INJECTION]: The skill includes patterns for processing external IFC (Industry Foundation Classes) data. It correctly identifies ingestion points for element properties and geometry, representing a surface for indirect prompt injection if malicious data within an IFC model is processed and subsequently used in an LLM prompt without sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 06:30 PM