The Agent Skills Directory

[SAFE]: Detailed analysis of the skill's instructions and templates revealed no malicious patterns, prompt injections, or unauthorized data exfiltration behaviors.
[DATA_EXFILTRATION]: The skill facilitates local data persistence using standard iOS/macOS mechanisms such as UserDefaults, FileManager (Application Support directory), and @SceneStorage. It includes a security best-practice warning advising users to utilize the Keychain for sensitive data instead of the generated state restoration system.
[COMMAND_EXECUTION]: The skill utilizes Glob, Grep, and Bash tools for project context detection (e.g., checking Swift versions and existing navigation patterns). These operations are restricted to project inspection and are consistent with the skill's stated purpose as a code generator.
[REMOTE_CODE_EXECUTION]: No external downloads or remote script executions were identified. All generated code is derived from the static templates provided within the skill package (templates.md).

state-restoration