李诞写作心法

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:34 PM UTC
• Version:
  0.1.0

Overview

This is a writing-style skill with a simple local article checker, and its behavior matches its stated purpose.

Install this if you want a Chinese long-form writing framework for explanatory articles. Be aware it may activate for broad writing or explanation requests and steer outputs into this style. Only run the quality-check script on article files you intend it to read.

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: 86% confidence
• Finding: The trigger conditions are broad enough to activate on many ordinary requests such as 'explain X' or 'write an article about X,' which can cause the skill to override user intent unexpectedly. Over-broad auto-activation can lead to prompt hijacking of benign workflows, forced formatting, and reduced user control over how the assistant responds.

Natural-Language Policy Violations

Medium

• Confidence: 77% confidence
• Finding: The skill strongly prescribes Chinese-language style and output behavior without checking user language preference or declaring a justified locale restriction. While not a classic security bug, this can create policy and control issues by causing unintended language switching, misleading outputs, or poor interoperability in broader agent workflows.

VirusTotal

66/66 vendors flagged this skill as clean.