Internationalizing Websites
Warn
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (MEDIUM): The skill instructs the agent to execute local scripts 'scripts/i18n-add-languages.mjs' and 'scripts/i18n-add-schema.js' to modify project configuration and create new language files. These scripts are not part of the skill payload, making their behavior unverifiable and requiring manual review to ensure they do not perform unauthorized file or network actions.
- [PROMPT_INJECTION] (LOW): The skill contains an Indirect Prompt Injection surface. 1. Ingestion points: curl command in Step 6 fetches sitemap.xml from an external URL. 2. Boundary markers: Absent; the content is processed directly by the agent. 3. Capability inventory: The agent has local command execution (node, npm, ls) and file modification capabilities. 4. Sanitization: Absent; external sitemap content is not filtered. The risk is rated LOW (Tier: internal influence) because the content is used for validation and reasoning rather than being directly passed to execution functions.
Audit Metadata