write-script-powershell
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the
wmillCLI, specificallywmill script preview,wmill script run, andwmill generate-metadata. These commands involve executing PowerShell code and modifying local configuration files. - [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection where user-supplied input is interpolated into command arguments.
- Ingestion points: User-provided arguments are passed to the
-dflag inwmill script preview <path> -d '<args>'(referenced in SKILL.md). - Boundary markers: No specific boundary markers or escape characters are defined for the interpolated arguments.
- Capability inventory: The agent can execute arbitrary PowerShell code through the preview tool and push changes to a workspace using
wmill sync push(referenced in SKILL.md). - Sanitization: The instructions do not explicitly provide logic for sanitizing or validating user-provided arguments before they are passed to the shell command.
Audit Metadata