The Agent Skills Directory

[SAFE]: The skill instructs the agent to perform standard development tasks using official Flutter and Dart commands, such as flutter gen-l10n, flutter analyze, and dart run intl_translation. No suspicious network activity, data exfiltration, or obfuscation techniques were identified.
[INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes developer-supplied project files.
Ingestion points: Reads pubspec.yaml, l10n.yaml, and *.arb files from the project directory.
Boundary markers: None explicitly defined in the instructions, though it relies on standard JSON and YAML formats.
Capability inventory: Executes shell commands via flutter and dart CLIs to generate and analyze code.
Sanitization: The skill instructions do not specify sanitization; it relies on the internal logic of the standard Flutter localization tools to handle data from ARB files safely.

flutter-internationalization