storybook-setup
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
npx storybook ai setup. This is a legitimate command provided by the vendor (storybookjs) to automate configuration tasks. - [PROMPT_INJECTION]: The instructions require the agent to "Follow the printed Markdown precisely" from the command's output and explicitly forbid substituting its own plan. This creates an indirect prompt injection surface because the agent is instructed to prioritize and execute potentially arbitrary instructions contained within external tool output.
- Ingestion points: Dynamically generated Markdown output from the
npx storybook ai setupcommand. - Boundary markers: Absent. The skill does not use delimiters or instructions to treat the command output as untrusted data.
- Capability inventory: The agent has the capability to modify project files and execute shell commands as part of the setup process.
- Sanitization: None. The agent is directed to follow the output "precisely" without validation.
Audit Metadata