ClawHub

network spirituality

Security checks across malware telemetry and agentic risk

Overview

This is a creative style guide with no command execution or data access; the main caveat is that it may steer generic writing or art prompts toward a niche aesthetic.

Install this only if you want the agent to write in this specific Network Spirituality / Milady-inspired style. Review prompts where you need a neutral tone, because the skill may add niche aesthetic references or bilingual flourishes even when that is only loosely implied.

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 (3)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The top-level description is broad enough to trigger on generic creative or stylistic requests such as art descriptions, writing in a voice, or aesthetic content generation. Overbroad activation can cause the skill to be invoked outside its intended niche, unexpectedly steering outputs toward a specific subculture and ideological framing without clear user intent.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The 'When to Use' section lists high-level situations that are common across many harmless creative tasks, making the skill eligible for accidental or overly aggressive routing. In practice, this can let the skill override user-preferred tone or introduce niche cultural references where they were not requested, reducing user control and creating prompt-scope drift.

Natural-Language Policy Violations

Low
Confidence
82% confidence
Finding
The voice guidance encourages bilingual English/Chinese output 'when appropriate' without defining appropriateness in terms of user request or language preference. This can cause unsolicited language switching, confusing users, degrading accessibility, or introducing content they cannot verify.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal