book-translation

Pass

Audited by Gen Agent Trust Hub on Oct 3, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides standard shell commands for file management (mkdir, cp) and project-specific script execution (node scripts/check-translations.js, npm run dev). These are typical operations for a developer tool and are scoped to the project's local directory.
  • [INDIRECT_PROMPT_INJECTION]: The skill guides the agent to process and translate MDX and JSON files from the repository. While this involves reading external data into the prompt context, the instructions focus on structural preservation and prose translation within the project's known file structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 3, 2026, 11:46 AM