spree-i18n
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for managing translations of merchant-provided content (e.g., product names, descriptions, and UI strings). This creates a vulnerability surface where malicious instructions could be embedded in external translation data to influence the agent during runtime processing.
- Ingestion points: Data entering the system via the 'spree_product_translations' database tables or 'config/locales/*.yml' translation files.
- Boundary markers: No specific delimiters or warnings for the agent to ignore instructions embedded in the translation content are mentioned.
- Capability inventory: The skill involves database updates ('product.update'), file system writes (modifying YAML locale files), and execution of local CLI tools ('i18n-tasks').
- Sanitization: There are no instructions for validating or sanitizing the content of the translations before they are processed or stored.
Audit Metadata