modern-frontend-design
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to verify the generated project, including
npm install,npm run build, andnpm run dev. It also usescurlfor a local health check onlocalhost:3000as specified in Step 12 ofSKILL.md. - [DYNAMIC_EXECUTION]: The skill generates application source code (Next.js, Tailwind) based on user templates and then executes it through the build and development commands.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user prompts to drive code generation, creating a potential injection surface.
- Ingestion points: User prompts for product design and requirements (Step 1 in
SKILL.md). - Boundary markers: Absent; no instructions are provided to the agent to delimit user input or ignore embedded malicious directives.
- Capability inventory: The agent executes package management and server commands (
npm,npx,curl) on the generated code (Step 12 inSKILL.md). - Sanitization: Absent; the user input is used for generation without validation or sanitization.
Audit Metadata