vibe-coding
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as "npm install", "npm run dev", and "npx create-next-app@latest" to scaffold and run web projects locally.
- [EXTERNAL_DOWNLOADS]: Fetches templates and references official documentation from well-known technology providers and organizations including Vercel (Next.js), React, and Tailwind CSS.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted user descriptions to drive code generation and local command execution. 1. Ingestion points: Processes user-provided "Application description" and "Feature requirements" as seen in the Inputs section of SKILL.md. 2. Boundary markers: Absent; there are no specific delimiters or instructions to ignore embedded commands within the user-provided vibes. 3. Capability inventory: Extensive local capabilities including file writing, directory initialization, and subprocess execution using package managers (SKILL.md). 4. Sanitization: Absent; the skill does not explicitly describe validation or sanitization of user-provided feature descriptions before they are translated into code or commands.
Audit Metadata