ifc-core-version-evolution
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as an informational reference and documentation set. It does not include executable scripts, shell commands, or automated routines that could perform unauthorized actions on the host system.
- [EXTERNAL_DOWNLOADS]: The skill provides links to official documentation, release notes, and development repositories from buildingSmart (e.g., technical.buildingsmart.org and github.com/buildingSMART). These are industry-standard resources for the IFC specification and are documented for informational purposes.
- [DATA_EXFILTRATION]: No patterns of data collection, credential harvesting, or exfiltration to third-party domains were found. All network-related content consists of standard HTTPS links to documentation pages.
- [PROMPT_INJECTION]: The instructions provide logical branching for the agent based on schema versioning (e.g., reading the FILE_SCHEMA header). There are no attempts to override agent safety constraints, bypass system instructions, or extract system prompts.
- [COMMAND_EXECUTION]: The skill does not contain any shell commands, subprocess invocations, or privilege escalation attempts.
Audit Metadata