The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The skill provides shell command templates (diff, grep, head) for validating translation integrity. These commands are used locally on documentation files and do not involve untrusted input or elevated privileges.- [INDIRECT_PROMPT_INJECTION] (LOW): The skill processes untrusted Markdown and MDX content. While there is a risk of instructions being embedded in source text, the skill provides extensive MDX safety rules and formatting requirements to mitigate rendering errors and accidental execution.- [DATA_EXFILTRATION] (SAFE): No external network calls, hardcoded credentials, or access to sensitive system configuration files were detected in the skill instructions.

article-translator