devexpress-office-file-api-spreadsheet

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external spreadsheet files (.xlsx, .xls, .csv, .txt), which serves as an ingestion point for untrusted data and potential indirect prompt injection attacks.\n
  • Ingestion points: Untrusted files are loaded using the workbook.LoadDocument method, as shown in SKILL.md and references/getting-started.md.\n
  • Boundary markers: The skill does not define specific text delimiters for prompt boundaries but focuses on API-level data handling.\n
  • Capability inventory: The API possesses capabilities for file system writes (SaveDocument), data rendering (ExportToPdf), and complex calculation of workbook formulas.\n
  • Sanitization: The references/safe-spreadsheet-processing.md guide provides high-quality remediation instructions for using WorkbookSecurityLoadingLimits (DoS protection) and WorkbookSecurityLoadingOptions to strip macros, OLE objects, and external connections during the load process.\n- [EXTERNAL_DOWNLOADS]: The skill references official DevExpress NuGet packages for its core functionality.\n
  • Evidence: It specifies DevExpress.Document.Processor, DevExpress.Drawing.Skia, and DevExpress.Pdf.SkiaRenderer. These are recognized vendor resources from DevExpress and are considered safe for use in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 12:06 PM