check-spelling

Pass

Audited by Gen Agent Trust Hub on May 6, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local shell command that pipes file names to a PowerShell script (./eng/common/spelling/Invoke-Cspell.ps1) located within the project repository.
  • [PROMPT_INJECTION]: Instructions include a human-in-the-loop requirement, directing the agent to prompt the user for confirmation before replacing misspelled words or updating configuration files. This prevents the agent from making autonomous, potentially destructive changes to the source code based on file content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 6, 2026, 02:30 PM