The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local validation script using node scripts/find-missing-translations.js to ensure translation coverage for the extension locales.\n- [INDIRECT_PROMPT_INJECTION]: The skill involves processing and editing user-facing translation strings in JSON files across multiple locales. Evidence chain: 1. Ingestion points include translation source files in src/i18n/locales/ and webview-ui/src/i18n/locales/, and the guidance file .roo/guidance/roo-translator.md. 2. No explicit boundary markers or instructions to ignore embedded commands within strings are present. 3. Capabilities include file modifications via apply_diff and local script execution via node. 4. No sanitization or content validation of the strings is specified, making this a standard surface for indirect prompt injection.

roo-translation