write-script-postgresql
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 via the
wmillCLI, includingwmill script preview,wmill script run, andwmill generate-metadata. These commands are used to test and manage scripts within the Windmill developer workflow. - [INDIRECT_PROMPT_INJECTION]: The skill accepts user-supplied arguments that are interpolated into shell commands for script execution (e.g.,
wmill script preview <path> -d '<args>'). - Ingestion points: User-supplied script arguments are ingested through command-line flags during the preview process.
- Boundary markers: The command template uses single quotes to wrap user arguments.
- Capability inventory: The agent has the capability to execute shell commands and trigger the execution of database logic with potential side effects.
- Sanitization: The instructions do not specify any mandatory sanitization or validation of the user-provided arguments.
- [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The
wmill generate-metadatacommand resolves and updates project dependencies. The instructions mitigate risk by requiring the agent to notify the user of any dependency version changes detected during this operation.
Audit Metadata