book-translation

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (LOW): (Category 8
  • Indirect Prompt Injection) The skill directs the agent to ingest and translate MDX and JSON files, which creates a surface for potential indirect prompt injection if the source text contains malicious instructions.\n
  • Ingestion points: MDX chapter files in src/content/book/ and JSON localization files in messages/.\n
  • Boundary markers: Absent; there are no instructions for the agent to ignore or delimit embedded directives within the book content.\n
  • Capability inventory: Filesystem operations (mkdir, cp), script execution (node scripts/check-translations.js), and development server execution (npm run dev).\n
  • Sanitization: Absent; the skill does not include steps to validate or escape the content being translated.\n- COMMAND_EXECUTION (SAFE): The shell commands provided (mkdir, cp) and the scripts mentioned (node, npm) are standard repository maintenance tasks and do not target sensitive system files or involve unauthorized network access.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:14 PM