ZeeLin Academic Paper

• Outcome: Pass
• Latest audit: May 29, 2026, 8:14 PM
• Version:
  1.0.1

Overview

This is a prompt-only Chinese STEM paper-writing helper with no executable code or hidden data-transfer behavior found.

Install from ClawHub or another verified source, grant only the file access needed for templates and drafts, and do not treat the privacy promises as a guarantee about the broader AI platform or host runtime. Generated academic content should be reviewed for accuracy, citations, originality, and any simulated data before use.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Intent-Code Divergence

Medium

• Confidence: 93% confidence
• Finding: The skill makes strong privacy and deployment assurances such as fully local processing, no external API calls, and no data leakage risk, but a markdown skill file cannot technically enforce or verify those runtime properties. This can mislead users into sharing sensitive research content under false assumptions, creating privacy and confidentiality risk if the hosting agent or surrounding platform does transmit data externally.

VirusTotal

66/66 vendors flagged this skill as clean.