microsoft-excel

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes data from external Excel workbooks, which is a vector for indirect prompt injection.
  • Ingestion points: External workbook content is fetched via the Microsoft Graph API in SKILL.md.
  • Boundary markers: None identified in the prompt logic to separate data from instructions.
  • Capability inventory: The skill executes curl and jq commands.
  • Sanitization: The skill does not sanitize the workbook data before presenting it to the model.
  • [COMMAND_EXECUTION]: The skill uses curl and jq to perform authorized operations against the Microsoft Graph API.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 02:27 AM
Security Audit — agent-trust-hub — microsoft-excel