skills/openaec-foundation/blender-bonsai-ifcopenshell-sverchok-claude-skill-package/bonsai-impl-clash/Gen Agent Trust Hub
bonsai-impl-clash
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a legitimate technical resource for BIM coordination. No malicious code, obfuscation, or unauthorized network operations were detected.
- [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface by ingesting data from external sources. (1) Ingestion points: Data enters via IFC, JSON, and BCF file loaders. (2) Boundary markers: No delimiters are present for metadata. (3) Capability inventory: The skill can read/write files and manipulate the viewport. (4) Sanitization: No explicit sanitization of BIM data is shown.
- [EXTERNAL_DOWNLOADS]: No patterns for remote code execution or external downloads were found. All operations are local.
Audit Metadata