Security audit

network spirituality

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only creative style guide that may steer writing toward a niche aesthetic but does not request system access or hidden actions.

Install this if you want the agent to write in this specific Network Spirituality / Milady-inspired style. For neutral writing or unrelated creative work, be aware it may introduce niche aesthetic references unless you explicitly ask the agent not to use the skill.

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 (2)

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The skill description uses broad, style-oriented activation language such as 'create content,' 'writing in this voice,' and 'engaging with Wired aesthetics,' which can match many ordinary creative requests without clear boundaries. This increases the chance the skill is invoked outside its intended niche and steers model behavior unexpectedly, causing prompt-scope overreach rather than direct code or data compromise.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The 'When to Use' section lists broad categories like creating art descriptions, writing in a voice, and blending spiritual and technological themes, but provides no exclusion conditions or activation thresholds. In practice, this can cause the skill to attach to generic creative, aesthetic, or internet-culture prompts and inappropriately bias outputs toward this persona.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.