glot-i18n
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): The skill follows a standard instructional format and does not contain attempts to bypass safety filters or ignore system instructions.
- [Data Exposure & Exfiltration] (SAFE): File access is limited to the project directory for the purpose of translation. No sensitive credentials or system files are accessed.
- [Remote Code Execution] (SAFE): No remote scripts or unverified binary executions were detected.
- [Indirect Prompt Injection] (SAFE): The skill reads project source code to identify strings for translation. 1. Ingestion points: scan_hardcoded and scan_untranslated tools read from files in project_root_path. 2. Boundary markers: The workflow instructions provide structural separation, though no explicit 'ignore instructions' markers are added to the prompt. 3. Capability inventory: Modification of local source code and JSON locale files. 4. Sanitization: None required for the intended i18n operations.
Audit Metadata