bonsai-impl-qto

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, hardcoded credentials, or unauthorized network operations were detected. The skill provides legitimate technical documentation for BIM workflows.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection (Category 8) due to its handling of external data.
  • Ingestion points: The skill ingests data from external IFC files through elements retrieved via tool.Ifc.get() and tool.Ifc.get_entity() as shown in references/examples.md.
  • Boundary markers: No specific delimiters or safety instructions are used to separate ingested IFC property data from the agent's core instructions.
  • Capability inventory: The skill has access to exploitable capabilities including modifying the IFC database via ifcopenshell.api.run and executing Blender operations through bpy.ops.bim operators.
  • Sanitization: No explicit sanitization or validation of data from the IFC element property sets is documented before use in automated calculations or agent decisions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 02:17 PM
Security Audit — agent-trust-hub — bonsai-impl-qto