The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes several system-level shell commands including npx, pnpm, and docker to perform scaffolding, install dependencies, and run validation smoke tests. These commands incorporate variables provided by the user during the input phase.- [PROMPT_INJECTION]: The skill demonstrates a vulnerability surface for indirect prompt injection or command injection because user-controlled inputs are interpolated directly into shell command templates without sanitization.
Ingestion points: User inputs PROJECT_NAME and APP_PORT are collected in SKILL.md and used to build command strings.
Boundary markers: No delimiters or explicit instructions are provided to the agent to treat these inputs as literal strings rather than potentially executable code.
Capability inventory: The skill possesses the capability to execute arbitrary commands via npx and pnpm, and can interact with the host filesystem and Docker daemon.
Sanitization: There is no evidence of validation or escaping to prevent shell metacharacters in the PROJECT_NAME or APP_PORT variables from altering the intended command execution flow.- [EXTERNAL_DOWNLOADS]: The skill fetches the create-next-app utility and several development packages from the NPM registry. Note that create-next-app is an official tool from Vercel, a well-known service.

architect-nextjs-vercel-app