next-intl-i18n

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or unauthorized network operations were detected. The skill only manages translation strings and routing.
  • [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill uses the established 'next-intl' library. The dynamic import of message files in i18n/request.ts is protected by a whitelist check (locales.includes(locale)), which prevents an attacker from supplying malicious paths via the URL.
  • [Prompt Injection] (SAFE): No override markers, role-play injections, or instructions to ignore safety guidelines were found in the skill metadata or body.
  • [Indirect Prompt Injection] (SAFE):
  • Ingestion points: The locale is ingested from the request/URL parameter in i18n/request.ts and app/[locale]/page.tsx.
  • Boundary markers: Translation messages are stored in structured JSON files.
  • Capability inventory: The skill does not perform any dangerous operations like exec, eval, or external network writes.
  • Sanitization: The locale input is strictly validated against a hardcoded array of supported locales before being used to load message files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:14 PM