lovstudio-translation-review

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill workflow involves executing shell commands to run pandoc for document conversion. It uses variables for filenames (e.g., "<chinese_file>.docx") which may be vulnerable to command injection if a user provides a filename containing shell metacharacters.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted content from external files (Chinese source and English translation) without employing boundary markers or explicit instructions to ignore embedded commands.
  • Ingestion points: Document reading logic in Step 2 of SKILL.md.
  • Boundary markers: Absent; content is read directly into the agent's context for comparison.
  • Capability inventory: Includes shell command execution (pandoc) and file-system write access for saving the final report.
  • Sanitization: No validation or sanitization of document content is performed before it is analyzed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of pandoc, a well-known document conversion tool, suggesting the use of external package managers like Homebrew.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 09:43 AM