write-script-mssql
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the
wmillCLI, such asscript previewto test local edits andgenerate-metadatato synchronize dependency locks and input schemas. These commands are essential for the skill's primary function of script development. - [DYNAMIC_EXECUTION]: The skill facilitates the creation and execution of dynamic code, specifically MS SQL Server queries and script entry points in Python and TypeScript. It provides specific syntax for parameter handling and result streaming.
- [INDIRECT_PROMPT_INJECTION]: It describes the use of a
prompt_for_aifield within script metadata, which allows script authors to provide natural language instructions directly to the AI to guide argument selection. This represents an intended surface for instructions to influence agent behavior during script execution.
Audit Metadata