ClawHub
Back to skill

Security audit

鲁迅先生写作手法

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only writing-style skill that may over-activate on broad Chinese writing prompts, but it does not request sensitive access or perform hidden actions.

Install this if you specifically want a forceful Lu Xun-inspired critique and rewrite style. Be aware it may apply a colder, anti-sentimental tone when prompts use broad terms like '怀疑' or '力量感', so users should invoke it explicitly for best control.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger list includes broad, common phrases such as '不要鸡汤', '怀疑', and '力量感' that can match ordinary writing requests unrelated to this specialized style. Overbroad activation can cause the skill to hijack general prompts and steer outputs toward a harsher, more ideological transformation than the user intended, reducing user control and causing inappropriate behavior in benign contexts.

Static analysis

No suspicious patterns detected.