The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local validation script (node scripts/find-missing-translations.js) to ensure translation coverage. This is a standard development utility within the repository.
[PROMPT_INJECTION]: The instructions include a directive to suppress output of translated text to the user interface ("Do not output the translated text into the chat, just modify the files"). While this reduces the visibility of changes for human review, it appears to be a productivity-oriented instruction intended for large-scale translation tasks.
[PROMPT_INJECTION]: Indirect Prompt Injection Surface:
Ingestion points: The agent reads and processes untrusted data from localization files (src/i18n/locales/, webview-ui/src/i18n/locales/) and source code files.
Boundary markers: None identified. There are no instructions for the agent to ignore potentially malicious instructions embedded within the translation strings themselves.
Capability inventory: The agent has the capability to modify files using apply_diff and execute local scripts via node (specifically scripts/find-missing-translations.js).
Sanitization: No sanitization or validation of the content of translation strings is mentioned before they are processed or written to files.

translation