skills/openaec-foundation/blender-bonsai-ifcopenshell-sverchok-claude-skill-package/ifcos-impl-validation/Gen Agent Trust Hub
ifcos-impl-validation
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains standard instructional material and code snippets for architectural data validation. No malicious patterns such as data exfiltration, obfuscation, or remote code execution were detected.
- [PROMPT_INJECTION]: The skill processes untrusted external data (IFC and IDS files), which represents a potential surface for indirect prompt injection.\n
- Ingestion points: The skill reads IFC model files via
ifcopenshell.open()and IDS specification files viaifctester.open().\n - Boundary markers: No explicit boundary markers or instructions to ignore embedded content are used when processing these files.\n
- Capability inventory: The skill has the capability to write files (HTML, JSON, BCF, ODS, XML) using reporter objects and the
to_file()orto_xml()methods.\n - Sanitization: No specific sanitization of the model data is performed prior to report generation, though the risk is minimized as the data is not interpreted as instructions.
Audit Metadata