i18n-localization
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a Python utility
scripts/i18n_checker.pydesigned to be run by the agent to analyze local source code files.\n- [PROMPT_INJECTION]: The audit script processes untrusted data from the user's project files, which could theoretically contain instructions intended to manipulate the agent's behavior when it reviews the script's output.\n - Ingestion points:
scripts/i18n_checker.pyreads code from .jsx, .tsx, .vue, .py, .json, and .po files.\n - Boundary markers: No specific delimiters or safety instructions are used when displaying snippets of discovered hardcoded strings.\n
- Capability inventory: The script performs local file reads; the agent using it likely has broader capabilities such as file modification or further command execution.\n
- Sanitization: Found strings are reported directly to output without escaping or sanitization.
Audit Metadata