ClawHub
Back to skill

Security audit

Metal Lyrics

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only metal lyric writing guide with disturbing artistic themes, but it does not install code, request secrets, or perform system actions.

Install only if you want a dark metal songwriting assistant and are comfortable policing the content it may produce. Do not grant it purchasing, crypto, credential, filesystem, or network tools; the artifact does not need them. Add your own safety limits if you will use it around minors, vulnerable users, real tragedies, targeted people, extremist themes, self-harm, or coercive relationship content.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill is explicitly designed to generate lyrics involving gore, self-harm, addiction, extremist politics, and other disturbing themes, yet it provides no user-facing safety boundary or content warning. In practice, this increases the risk that the agent will produce harmful or destabilizing content for vulnerable users under an artistic framing without caution or refusal logic.

Ssd 4

Medium
Confidence
94% confidence
Finding
This section gives explicit creative methodology for writing from a predator's perspective, using scent-tracking, stalking, and pursuit as emotionally resonant devices. Although framed as lyric craft, it operationalizes predatory-role narration and can be used to generate obsession or stalking content that normalizes coercive behavior.

Ssd 4

Medium
Confidence
96% confidence
Finding
This section provides a step-by-step method for transforming true-crime violence into usable lyrical material using detached, report-like narration and dark wordplay. That is dangerous because it lowers the barrier to generating exploitative, desensitizing, or copycat-oriented depictions of real violence while explicitly avoiding moral framing.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.