english-tutor

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFENO_CODEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious activities or security threats were identified. The skill acts as a standard educational assistant for English language learning.
  • [NO_CODE]: The skill consists exclusively of instructional Markdown and does not include executable scripts or binaries.
  • [EXTERNAL_DOWNLOADS]: The skill suggests an optional installation command for an additional tool hosted on GitHub (github:mindverse/skillhub). This is a transparent recommendation intended for users seeking additional capabilities and does not involve automated execution.
  • [PROMPT_INJECTION]: The skill processes external text for grammar correction, which presents a surface for indirect prompt injection (Ingestion: '用户原文' in SKILL.md; Boundary markers: absent; Capability inventory: text generation; Sanitization: absent). However, the risk is limited as the agent's actions are restricted to text-based educational responses and it lacks access to high-privilege tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 03:44 PM