ifcos-impl-profiles

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill implementation follows best practices for BIM data manipulation and uses standard well-known libraries like IfcOpenShell and NumPy.
  • [PROMPT_INJECTION]: The skill demonstrates processing of IFC data which represents a surface for indirect prompt injection via entity attributes. 1. Ingestion points: ifcopenshell.open() in references/examples.md. 2. Boundary markers: Not present; the skill treats IFC attribute data as standard strings. 3. Capability inventory: The skill possesses the ability to modify BIM models and write them to the local file system using model.write(). 4. Sanitization: Not explicitly implemented for the strings processed from IFC entities.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 06:31 PM