The Agent Skills Directory

[SAFE]: The skill's operations are consistent with its described purpose. It lacks any patterns associated with data exfiltration, unauthorized privilege escalation, or malicious persistence.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted translation strings from PO files and source code, creating a surface for indirect prompt injection.
Ingestion points: PO files in the languages/ directory and strings extracted from source code.
Boundary markers: No delimiters or isolation markers are defined for the strings being translated.
Capability inventory: The skill utilizes Read, Write, Edit, Bash, and Agent tools.
Sanitization: There is no logic for sanitizing or escaping the content of the translation strings before they are processed.

premium-translate