The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The scripts/add-frontend-app.py script performs file system operations (creating directories and writing text files) but only within a user-defined project root. It does not spawn arbitrary shells or execute external commands without authorization.
[CREDENTIALS_UNSAFE] (SAFE): Documentation and templates (e.g., deployment-guide.md) mention environment variables like CLERK_SECRET_KEY and MONGODB_URI, but these are provided as placeholders (e.g., sk_...) for user configuration. No live secrets are hardcoded.
[EXTERNAL_DOWNLOADS] (SAFE): GitHub Action workflows utilize trusted sources such as actions/checkout and oven-sh/setup-bun. No downloads from untrusted or suspicious domains were found.
[DATA_EXFILTRATION] (SAFE): The provided code and templates do not contain logic for reading sensitive system files (e.g., SSH keys, AWS creds) or transmitting data to unauthorized external endpoints.
[PROMPT_INJECTION] (SAFE): No instructions designed to override agent behavior, bypass safety filters, or extract system prompts were detected in the markdown or code comments.

fullstack-workspace-init