korean-character-count
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local script
scripts/korean_character_count.jsto process text input. This execution is deterministic and follows the specified workflow for character counting without using external or untrusted binaries. The script uses standard Node.js argument parsing and does not pass input to a shell, preventing command injection.- [SAFE]: The implementation relies exclusively on standard Node.js built-in modules (node:fs) and the native UnicodeIntl.SegmenterAPI. It does not require external package installations (nopackage.jsonor external dependencies) or network connectivity.- [SAFE]: File reading is performed usingfs.readFileSyncon paths provided as arguments. The script only outputs numerical metadata and contract descriptions; it does not exfiltrate or echo the contents of the files it processes, maintaining data privacy.
Audit Metadata