The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes external data that could contain malicious instructions.
Ingestion points: The skill reads untrusted content from README.md and README.zh-TW.md via the read_file tool.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the file content strictly as data or to ignore any embedded instructions found within the text.
Capability inventory: The agent has the capability to modify local files using replace_string_in_file and list files using get_changed_files.
Sanitization: The instructions lack any sanitization, validation, or escaping logic to prevent the agent from executing instructions found within the README files during the translation process.

readme-i18n