Back to skill

Security audit

Metal Lyrics

Security checks for vulnerabilities and agentic risk

Overview

This skill is a static lyric-writing guide for metal genres, with dark and violent themes that are expected for the stated purpose but should be used knowingly.

Install this only if you want help writing metal lyrics and are comfortable with potentially disturbing themes such as violence, death, abuse, addiction, and self-harm imagery. It does not appear to access files, run code, use credentials, or persist changes.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill explicitly enables generation of lyrics involving self-harm, suicide, gore, abuse, and extreme violence across many subgenres, but its top-level description gives no user-facing warning about distressing or potentially harmful content. In a lyric-generation skill, this does not create direct code-execution risk, but it can expose unsuspecting users to triggering material and normalize unsafe content without informed consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The description states the skill 'Supports lyrics in English, German, Russian, and Japanese,' which defines supported language behavior but does not explicitly say the user chooses the language or that the default remains user-directed. Under locale policy, skills should offer language or locale choice rather than implicitly steering output into preset languages.

Content

No source excerpt is available for this finding.