write-workflow-as-code
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defines the use of the
wmillCLI to perform developer tasks such as previewing scripts, running workflows, and synchronizing code with the Windmill platform. This behavior is consistent with the primary purpose of the skill for thewindmill-labsauthor context. - [INDIRECT_PROMPT_INJECTION]: The agent is instructed to analyze script files to determine parameter types and generate appropriate test arguments for command-line execution. This establishes a processing chain where external code content influences the agent's execution parameters.
- Ingestion points: Script source code and metadata files (.script.yaml, .lock) described in
SKILL.md. - Boundary markers: None specified for the script parsing process.
- Capability inventory: Local command execution via the
wmilltoolset. - Sanitization: No explicit sanitization or validation of the parsed script arguments is mentioned.
Audit Metadata