The Agent Skills Directory

[SAFE] (SAFE): No malicious instructions, prompt injection, or obfuscation patterns were identified. The content is strictly instructional and follows standard software development practices.
[COMMAND_EXECUTION] (LOW): The skill documents the use of the shadcn-vue CLI for project initialization and component installation (e.g., npx shadcn-vue@latest init). These are expected operations for the library's primary purpose.
[EXTERNAL_DOWNLOADS] (LOW): Documents the ability to fetch component registries from remote URLs using the CLI. While this is an external download surface, the skill uses placeholder domains (acme.com) for demonstration and emphasizes the use of authenticated tokens for secure custom registries.
[CREDENTIALS_SAFE] (SAFE): The documentation mentions token-based authentication for private registries using the [SECURE_TOKEN] placeholder. No real API keys, secrets, or sensitive credentials are hardcoded in the skill.
[DATA_EXPOSURE] (SAFE): No access to sensitive file paths (e.g., SSH keys, env files) or unauthorized network exfiltration logic was found.

shadcn-vue