vrt-check
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to dynamically discover and execute shell commands from the local repository, such as
just,npm,yarn, and various VRT tools (Playwright, Storybook, Chromatic, Loki). This is a primary function for its intended use case of running and updating visual tests. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from the local repository and user input which is subsequently interpolated into shell commands, creating a potential surface for injection if the project files are malicious or compromised.
- Ingestion points: Project configuration files (
package.json,justfile,Makefile), directory listings, and the user-supplied--componentargument. - Boundary markers: No explicit boundary markers or warnings are used to distinguish instructions from the data being parsed from the repository.
- Capability inventory: The skill has the capability to execute shell commands across the local environment.
- Sanitization: There are no instructions to sanitize or validate strings discovered in configuration files or provided via arguments before they are interpolated into execution blocks like
just visual-update --story={name}.
Audit Metadata