write-script-powershell
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 perform operations using the wmill CLI tool, such as wmill script preview and wmill generate-metadata, which involve executing shell commands.
- [DYNAMIC_EXECUTION]: The skill involves the generation of PowerShell script files which are then executed by the agent for testing purposes using the wmill script preview command.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions tell the agent to follow instructions found in a prompt_for_ai field within script schemas. This is an ingestion point for data that could contain malicious instructions. 1. Ingestion points: prompt_for_ai field in script schemas. 2. Boundary markers: None. 3. Capability inventory: Command execution (wmill CLI) and file writing. 4. Sanitization: None.
Audit Metadata