ClawHub
Back to skill

Security audit

Unreasonable Hospitality

Security checks across malware telemetry and agentic risk

Overview

This is a text-only product and UX guidance skill with broad stylistic influence but no code execution, credential access, persistence, or hidden data handling.

Install this if you want a hospitality-oriented lens to shape UX, copy, feedback, and assistant interactions. Be aware it may activate across a wide range of product and writing tasks, so keep normal user-consent and data-access boundaries in place when applying its personalization advice.

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
94% confidence
Finding
The skill description is extremely broad and overlaps with many common product, UX, writing, feedback, and assistant-building tasks, which increases the chance of accidental or inappropriate invocation outside a narrowly intended context. That can cause this skill to steer agent behavior across a wide range of user requests, potentially overriding more suitable task-specific guidance and creating prompt-scope confusion.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.