write-script-ansible
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill documents the use of the
wmillCLI tool for script preview, running, and metadata generation, which are legitimate operations within the Windmill developer environment. - [CREDENTIALS_UNSAFE]: The instructions follow security best practices by requiring the use of resource-typed parameters for credentials and configuration instead of hard-coding secrets or reading from the environment.
- [EXTERNAL_DOWNLOADS]: Describes the configuration of Ansible Galaxy collections and Python pip dependencies within the script's header, which is the standard mechanism for managing environment requirements on the platform.
- [INDIRECT_PROMPT_INJECTION]: While the skill involves processing user input to generate and execute code, it provides clear guidance on distinguishing between local testing (
preview) and production deployment (push) to minimize accidental or malicious state changes.
Audit Metadata