write-workflow-as-code

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the wmill CLI tool for various development tasks, including local execution (wmill script preview), remote execution (wmill script run), and deployment (wmill sync push). These commands are essential for the skill's primary purpose as a developer assistant for the Windmill platform.
  • [INDIRECT_PROMPT_INJECTION]: The skill operates on user-provided code which is subsequently executed via the CLI. While this represents a standard developer workflow, it is a known attack surface for indirect prompt injection. The skill mitigates this by instructing the agent to confirm execution intent or only run previews when the user has explicitly requested to test their local changes.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 06:29 AM
Security Audit — agent-trust-hub — write-workflow-as-code