microsoft-excel

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and interacts with external API endpoints at gateway.maton.ai and ctrl.maton.ai to proxy requests to Microsoft Graph and manage user connections.\n- [PROMPT_INJECTION]: The skill presents an indirect prompt injection attack surface by processing external content.\n
  • Ingestion points: The skill retrieves cell values and table data from Excel spreadsheets stored in OneDrive through the /range and /tables endpoints defined in SKILL.md.\n
  • Boundary markers: No delimiters or isolation instructions are provided in the skill documentation to help the agent distinguish spreadsheet data from control instructions.\n
  • Capability inventory: The skill has the ability to read, write, create, and delete various Excel resources, including workbooks, worksheets, and tables.\n
  • Sanitization: The skill does not implement any apparent validation or sanitization of the data retrieved from the external workbooks before it is added to the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 04:48 AM