The Agent Skills Directory

[PROMPT_INJECTION]: No instructions were found that attempt to override agent behavior, bypass safety filters, or extract system prompts.
[CREDENTIALS_UNSAFE]: No hardcoded secrets, API keys, or private tokens are present; code examples use standard placeholders where appropriate.
[EXTERNAL_DOWNLOADS]: All external references and package installations target well-known, official sources from the TanStack and Effect-TS organizations.
[REMOTE_CODE_EXECUTION]: No patterns of executing remote scripts or unverified code were identified.
[COMMAND_EXECUTION]: Shell commands are restricted to standard project initialization and package management tasks (e.g., npm install, npm create).
[DATA_EXFILTRATION]: There is no evidence of unauthorized data collection or exfiltration of sensitive information to external domains.
[DATA_EXPOSURE]: The skill does not attempt to access sensitive local files, environment variables, or system configurations.
[SAFE]: The skill serves as a legitimate technical guide, encouraging the use of runtime validation and type safety to improve application security and stability.

tanstack-stack