japanese-product-localization
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted external data and possesses the capability to execute shell commands via project tools.
- Ingestion points: The skill is designed to process external resources including JSON, YAML, PO, and ARB locale files, as well as ICU messages (SKILL.md).
- Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions that might be embedded within the localization strings or resource files.
- Capability inventory: In
references/resource-integrity-and-qa.md, the agent is instructed to "Run the repository’s parser, linter, type check, localization compiler, and snapshot or UI tests," which involves executing shell commands that could be influenced by malicious content in the processed files. - Sanitization: There is no evidence of sanitization, validation, or filtering of the external content before it is processed by the agent or the repository tools.
- [SAFE]: The skill references authoritative external resources from trusted organizations, including Google (Material Design), the Unicode Consortium (CLDR), the World Wide Web Consortium (W3C), and the Japan Translation Federation (JTF). These references are used for legitimate technical and linguistic guidance.
Audit Metadata