The Agent Skills Directory

[SAFE]: The skill provides educational content and a static analysis tool for software localization. All included code is transparent, follows best practices, and performs only local file system operations within the scope of its defined purpose.
[INDIRECT_PROMPT_INJECTION]: The script scripts/i18n_checker.py scans external project files provided as input, which constitutes an ingestion point for untrusted data. This finding is classified as safe because the script's capabilities are restricted to pattern matching via regex and reporting results as text; it does not execute the ingested content or perform network operations.
Ingestion points: scripts/i18n_checker.py reads file content using Path.read_text.
Boundary markers: None; the script performs raw regex matching on file contents.
Capability inventory: Local file system access using the pathlib module for reading and directory traversal.
Sanitization: No sanitization is performed on ingested data before matching, but the impact is limited to terminal output during the auditing process.

i18n-localization