i18n-expert
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script (scripts/i18n_audit.py) and use the rg search tool to scan project files for i18n keys and hard-coded UI strings.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code and locale files, creating a vulnerability surface where malicious instructions in these files could influence the agent during the audit process.\n
- Ingestion points: The scripts/i18n_audit.py script reads contents from the user's source code and JSON locale files located at paths provided via the --src and --locale arguments.\n
- Boundary markers: The audit results are presented to the agent without explicit boundary markers or isolation instructions to prevent the agent from following instructions found within the data.\n
- Capability inventory: The skill possesses the ability to execute shell commands, read local files, and write to locale files.\n
- Sanitization: There is no evidence of sanitization or validation of the extracted string keys before they are reviewed by the agent.
Audit Metadata