excel-accessibility
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references authoritative documentation from the World Wide Web Consortium (W3C) and Microsoft (support.microsoft.com, docs.microsoft.com) to provide users with remediation guidance. These links point to well-known, trusted organizations for web and software accessibility standards.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze untrusted data within
.xlsxfiles (specifically Open XML components likesharedStrings.xmlandworkbook.xml). This data is provided by users and could potentially contain malicious prompts intended to influence the agent's analysis behavior. However, the risk is mitigated by the skill's defined role as a read-only scanner. - Ingestion points: The skill reads cell text, sheet names, and properties from uploaded Excel files.
- Boundary markers: Analysis findings are structured into predefined templates (Rule ID, Severity, Location), which helps maintain separation between processed data and agent instructions.
- Capability inventory: The skill requires file system read access to analyze the workbook structure but does not include network write or local file write capabilities in its logic.
- Sanitization: The skill instructions do not explicitly describe sanitization for content extracted from the spreadsheet before including it in the output findings.
Audit Metadata