The Agent Skills Directory

[SAFE]: The skill instructions focus exclusively on document translation tasks. There are no instances of remote code downloads, shell command execution, or sensitive data exfiltration.
[PROMPT_INJECTION]: The skill processes external files provided by the user. While it lacks explicit boundary markers or instructions to ignore commands embedded within the documents being translated (Indirect Prompt Injection surface), this is typical for translation utilities and does not represent an active threat.
Ingestion points: Reads documents from paths provided by the user (SKILL.md).
Boundary markers: Absent.
Capability inventory: No file system writes or network operations detected.
Sanitization: Absent.

translate-doc