bonsai-impl-project

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external IFC data, which is an attack surface for indirect prompt injection.\n
  • Ingestion points: IFC files are loaded via ifcopenshell.open() and bpy.ops.bim.load_project() in SKILL.md and references/examples.md.\n
  • Boundary markers: No explicit delimiters or instructions to ignore instructions within the IFC data are used.\n
  • Capability inventory: The skill allows writing to the filesystem using model.write() and bpy.ops.bim.save_project().\n
  • Sanitization: No evidence of data sanitization or filtering of input IFC content is present.\n- [SAFE]: The skill's primary functionality is secure and well-documented.\n
  • Standard APIs: It correctly utilizes the high-level ifcopenshell.api for all BIM operations, avoiding low-level pitfalls.\n
  • Authoritative Sources: All external references and source links point to the official IfcOpenShell documentation and GitHub repository.\n
  • Best Practices: The instructions include specific warnings against invalid project setups and legacy module paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 06:31 PM
Security Audit — agent-trust-hub — bonsai-impl-project