skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/nobim-image-generator/Gen Agent Trust Hub
nobim-image-generator
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (Excel/IFC) to generate visualizations and reports, creating a surface for potential indirect prompt injection attacks.
- Ingestion points: The
load_from_excelmethod inSKILL.mdreads project data from user-supplied Excel files. - Boundary markers: The instructions lack explicit delimitation or warnings to ignore instructions embedded within the processed BIM data.
- Capability inventory: The skill can write files to the local filesystem (
plt.savefig,fig.write_image,c.save) and perform batch processing of multiple files. - Sanitization: No specific sanitization or validation of data content is performed before processing or interpolation into reports.
Audit Metadata