ifcos-impl-sequence

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Technical analysis of the skill confirms it is focused on providing valid API usage patterns for the IfcOpenShell library.
  • [SAFE]: No instances of prompt injection, data exfiltration, or obfuscation were found across the skill documentation and code examples.
  • [EXTERNAL_DOWNLOADS]: The skill references the standard ifcopenshell Python library, which is a well-known industry tool for BIM processing.
  • [COMMAND_EXECUTION]: All code examples demonstrate safe usage of the library's internal API dispatcher (ifcopenshell.api.run) without invoking arbitrary system commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes IFC files via ifcopenshell.open() and can write files via model.write(). Ingestion points: ifcopenshell.open() in SKILL.md. Boundary markers: Absent. Capability inventory: model.write() in SKILL.md. Sanitization: Absent. While this constitutes a data processing surface, it is consistent with the skill's primary purpose and no malicious exploitation patterns were found.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 06:31 PM