ClawHub
Back to skill

Security audit

Vague Requirement Unpacker

Security checks across malware telemetry and agentic risk

Overview

This skill is a benign product-management helper that structures vague requirements using local templates and does not request unusual access.

Installers should understand this skill may activate for broad Chinese-language requirement-unpacking requests and may ask users to confirm a local intake form. Avoid entering highly confidential business details unless the host environment is trusted.

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
88% confidence
Finding
The trigger list includes broad natural-language phrases such as '帮我判断这个需求该先问什么' and '帮我把这个模糊需求拆成能开会对齐的材料', which can plausibly appear in ordinary conversation outside the intended narrow workflow. In an agent-routing system, overly broad activation can cause unintended invocation of this skill, leading to misrouting, inappropriate form/UI prompts, or the agent following this skill's rigid process when the user wanted a different task.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.