article-translate

Warn

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the baoyu-translate skill from the jimliu/baoyu-skills repository for processing large documents. This introduces a dependency on external code from an unverified source.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted technical content (READMEs, source code, papers) without adequate security boundaries.
  • Ingestion points: External technical materials such as READMEs, papers, source code comments, and articles.
  • Boundary markers: No explicit delimiters or instructions are used to separate the untrusted source text from the agent's translation instructions.
  • Capability inventory: The skill utilizes AskUserQuestion and Skill tools, and it writes translation preferences to a local .article-skills directory within the project root.
  • Sanitization: There is no evidence of input validation, filtering, or sanitization performed on the content before translation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 8, 2026, 01:39 PM
Security Audit — agent-trust-hub — article-translate