ifc-syntax-classifications

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a static knowledge source for architectural data standards. It contains no executable code, remote script downloads, or network operations outside of references to official buildingSMART documentation.- [PROMPT_INJECTION]: The skill provides logic for processing external architectural models, which constitutes a surface for indirect prompt injection if ingested data contains malicious instructions. However, the skill focus is strictly on technical structural guidelines and schema compliance.
  • Ingestion points: Ingestion of external .ifc (STEP physical files) project data as described in the syntax reference.
  • Boundary markers: No explicit delimiters for untrusted attribute content are defined within the skill.
  • Capability inventory: Instructions for mapping and auditing relationships between building objects and external taxonomies.
  • Sanitization: No explicit sanitization or filtering of textual attribute values is mentioned in the provided guidance.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 04:40 PM
Security Audit — agent-trust-hub — ifc-syntax-classifications