Back to skill

Security audit

music-transposer

Security checks for vulnerabilities and agentic risk

Overview

The skill has a normal music-transposition purpose, but it asks for an API key and tells the agent to run a script that is not included in the artifact, leaving the real behavior unclear.

Review before installing. Only use it if you can verify the missing scripts/music_transposer.py implementation from a trusted source, use non-sensitive music inputs, choose an explicit output path that will not overwrite important files, and provide only a limited-purpose API key.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill’s activation criteria are broad enough that an agent could invoke it in situations only loosely related to music transposition, increasing the chance of unnecessary execution. Because the skill runs a script and is associated with file output and API-key use, ambiguous triggering expands exposure to unintended file writes or external-service usage.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documentation tells users to provide an input path, output path, and API key, but does not clearly warn that the skill writes files and depends on a secret for operation. This can lead to unsafe use, such as overwriting unexpected files, mishandling credentials, or invoking the skill without understanding that external resources or privileged data may be involved.

Content

No source excerpt is available for this finding.