The Agent Skills Directory

[PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection (Category 8) due to its core function of extracting strings from project files.
Ingestion points: The skill scans project components and pages for hardcoded strings as part of its automated workflow.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between extracted strings and operational instructions.
Capability inventory: The agent has the capability to install npm packages, modify configuration files, and write new locale files.
Sanitization: No sanitization or validation logic is specified for the content extracted from the source files before it is processed.
[EXTERNAL_DOWNLOADS]: The skill recommends installing standard and well-known internationalization libraries such as next-intl, react-i18next, and vue-i18n from official registries, which is consistent with its stated purpose.

i18n-automation