microsoft-excel

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx @useclawlink/cli, which fetches and executes the ClawLink CLI package from the public NPM registry.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands using the ClawLink CLI to perform Excel operations, such as npx @useclawlink/cli run microsoft-excel.
  • [DATA_EXPOSURE]: The documentation identifies that authentication credentials are stored locally in the user's home directory at ~/.clawlink/credentials.json. This is standard behavior for CLI-based authentication tools.
  • [INDIRECT_PROMPT_INJECTION]: The skill interacts with external data within Excel workbooks (e.g., reading or updating rows and tables). This creates a potential surface for indirect prompt injection if the workbook content contains malicious instructions intended to influence the agent's behavior.
  • Ingestion points: Data read from Microsoft Excel workbooks through actions like excel_add_table_row or excel_apply_table_filter.
  • Boundary markers: None specified in the instructions.
  • Capability inventory: The skill allows execution of CLI commands and network operations via the Microsoft Graph API.
  • Sanitization: Not explicitly defined within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:42 PM
Security Audit — agent-trust-hub — microsoft-excel