skills/impertio-studio/ifc-claude-skill-package/ifc-agents-migration-orchestrator/Gen Agent Trust Hub
ifc-agents-migration-orchestrator
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill ingests and processes external IFC files, which represents a surface for indirect prompt injection where malicious instructions could be embedded in metadata or string attributes.
- Ingestion points: The skill reads the STEP HEADER section and entity instances from the IFC dataset (SKILL.md, references/methods.md).
- Boundary markers: The process relies on structured field extraction but does not implement explicit natural language delimiters for data isolation.
- Capability inventory: The skill uses ifcopenshell and ifcpatch for file transformation and validation routing.
- Sanitization: The instruction set requires mandatory validation against target schemas to detect malformed or non-conformant output.
- [EXTERNAL_DOWNLOADS]: The skill references official documentation and validation services from buildingSMART and the IfcOpenShell project. These links point to well-known industry-standard domains for BIM data specifications.
Audit Metadata