localization-toolkit
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues were identified in the skill's instructions or scripts. The tool uses standard development practices for internationalization auditing.
- [COMMAND_EXECUTION]: The skill executes
ripgrepand a local Python script (scripts/i18n_audit.py) to scan source code and locale files. These are benign operations for the intended purpose of the skill. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the project being audited (source code and JSON locale files). * Ingestion points: Source files and translation files are read to extract keys. * Boundary markers: Absent. * Capability inventory: File reading and regex extraction across all files. * Sanitization: None. While this creates a theoretical surface for injection from the analyzed codebase, the limited scope of the audit operations and the specific regex-based extraction make it a low-risk environment.
Audit Metadata