ClawHub
Back to skill

Security audit

Emergent Generation

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed idea-generation methodology skill made of Markdown instructions and examples, with no executable code or hidden high-impact behavior found.

Install this if you want a Chinese-language framework for emergent-system ideation and structured solution generation. Use the exact skill name or specific trigger phrase when invoking it, and review its outputs as methodology guidance rather than verified facts or automatic actions.

SkillSpector

By NVIDIA
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
90% confidence
Finding
The trigger list contains broad generic phrases such as '简单规则' and '系统运行' that are likely to appear in many unrelated prompts, increasing the chance of accidental skill invocation. In a skill that defines execution flow and loads additional references, unintended activation can cause the agent to apply the wrong methodology or pull in extra instructions in contexts the user did not intend.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.