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 wmill CLI, specifically wmill script preview, wmill script run, and wmill 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 -d flag in wmill 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
Risk Level
SAFE
Analyzed
Aug 18, 2026, 04:44 AM
Security Audit — agent-trust-hub — write-script-powershell