baoyu-translate

Pass

Audited by Gen Agent Trust Hub on Nov 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from external files and URLs provided by the user. This data is analyzed for tone and terminology before being interpolated into translation prompts for both the main agent and subagents, creating a surface for indirect prompt injection attacks. Evidence includes the use of user-provided URLs as source material and the lack of explicit sanitization or delimiting markers in the prompt templates.
  • [COMMAND_EXECUTION]: The skill invokes the Bun runtime to execute its internal text processing scripts, specifically scripts/main.ts and scripts/chunk.ts, for document management and chunking.
  • [EXTERNAL_DOWNLOADS]: The instructions provide a mechanism to download and execute the Bun runtime from the official NPM registry via npx if it is not already installed on the system. This utilizes a well-known and trusted third-party package registry.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 2, 2026, 09:45 AM