Li Bin Perspective V2

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:35 PM UTC
• Version:
  1.0.0

Overview

This is a low-risk persona and strategy-guidance skill made of Markdown text, with no code execution, credential access, external calls, or persistence.

This appears safe to install from a security perspective. Treat it as a simulated public-information business perspective, not an official statement from Li Bin or NIO, and verify factual, financial, or strategic claims before relying on them.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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 (2)

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger phrases include common business terms such as “用户企业” and “换电模式,” which could be mentioned in ordinary discussion and unintentionally activate the skill. This is not a classic security exploit, but it can cause unintended persona takeover or response-shaping, especially in multi-skill environments where routing depends on loose phrase matching.

Natural-Language Policy Violations

Medium

• Confidence: 84% confidence
• Finding: The skill states that, once activated, it will respond in a fixed style without offering language choice, which can override user preference and reduce transparency about output constraints. In security terms this is a policy/control weakness rather than a direct exploit, but it can degrade user agency and create unexpected behavior in broader systems.

VirusTotal

65/65 vendors flagged this skill as clean.