react-setup
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes multiple shell commands to set up the development environment, including
pnpm create,pnpm install,mkdir, andrmfor project scaffolding and cleanup. - [EXTERNAL_DOWNLOADS]: The skill downloads numerous dependencies from the NPM registry and utilizes
pnpm dlx shadcn@latestto fetch and execute the shadcn CLI tool during the setup process. - [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to potential command injection via the user-supplied
{project}variable, which is interpolated directly into bash commands. - Ingestion points: The
{project}name provided by the user and used throughoutSKILL.md. - Boundary markers: Absent; the bash scripts do not use delimiters or warnings to prevent the agent from executing malicious characters embedded in the project name.
- Capability inventory: The skill has the capability to execute shell commands, write to the file system, and perform network requests via package managers.
- Sanitization: Absent; there are no instructions to validate or sanitize the project name before it is passed to the shell.
Audit Metadata