write-script-rlang

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill guides the agent on using the wmill CLI to preview, run, and sync R scripts. These commands are standard for the development workflow and include logic to avoid accidental deployment of untested changes.
  • [DATA_EXPOSURE]: The instructions describe using get_variable and get_resource to access sensitive data within the platform. This follows secure development practices by using the platform's secret management system rather than hardcoding credentials.
  • [REMOTE_CODE_EXECUTION]: The skill mentions wmill script preview, which executes local R code. The instructions provide clear constraints, ensuring the agent uses this command primarily for testing edits at the user's request and warns that execution may cause side effects.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 04:44 AM
Security Audit — agent-trust-hub — write-script-rlang