i18n-completeness
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill ingest data from project source files and translation keys which could contain malicious instructions. Evidence: (1) Ingestion points: File reading and Grep/Glob operations in SKILL.md. (2) Boundary markers: Absent. (3) Capability inventory: Bash execution and file editing. (4) Sanitization: Absent.
- [Command Execution] (LOW): The skill executes bash commands starting with 'bun run check:i18n*'. While limited to the local environment and specific script prefix, the wildcard allows for execution of any sub-commands defined in the project configuration.
Audit Metadata