ClawHub
Back to skill

Security audit

[Nyx Archive] Coding Philosophy

Security checks across malware telemetry and agentic risk

Overview

This appears to be a coding-workflow guidance skill with some transparency and scoping caveats, but no artifact-backed evidence of hidden access, persistence, credential use, exfiltration, or destructive behavior.

Install this only if you want the agent to follow the author's coding workflow preferences, including reading memory or notes first and being terse. Review the skill text if you prefer stronger boundaries around when it activates or more verbose agent explanations.

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
91% confidence
Finding
The skill is explicitly user-invocable but provides no bounded trigger conditions, allowed task scope, or refusal boundaries. That makes it easier for the skill to be activated in broad contexts and to influence coding workflows beyond its intended philosophical purpose, especially because it also contains operational guidance about editing code and workflow decisions.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.