write-script-graphql
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute various
wmillCLI commands, such aswmill script preview,wmill script run, andwmill generate-metadata. These are standard operational commands for the Windmill platform and are gated by user intent or specific project configuration files (e.g.,AGENTS.md). - [INDIRECT_PROMPT_INJECTION]: The skill mentions a platform-specific metadata field
prompt_for_aiused in input schemas to guide AI agents when selecting inputs. This is a documented feature of the Windmill platform for providing contextual instructions to agents and is handled here as part of standard metadata synchronization.
Audit Metadata