Back to skill

Security audit

Quicklrc Transcribe

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward QuickLRC transcription helper, with the main consideration being that submitted media URLs and optional lyrics are sent to QuickLRC for processing.

Install only if you are comfortable sending media URLs, YouTube links, and any provided lyrics to QuickLRC under your own API key. Avoid submitting private, confidential, or unauthorized copyrighted material unless you understand the provider's terms and data handling.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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)

External Transmission

Medium
Category
Data Exfiltration
Confidence
87% confidence
Finding

This skill is designed to call an external API using curl and an API key, which means user data and request metadata are transmitted outside the local agent boundary. In context this is expected functionality rather than overtly malicious behavior, but it is still security-relevant because it exposes supplied URLs, optional lyrics, and the bearer token to a third-party service if used improperly or without clear consent.

Content

Scanner excerpt · SKILL.md (reported line 11)May include surrounding context.

md
env:
        - QUICKLRC_API_KEY
      bins:
        - curl
    primaryEnv: QUICKLRC_API_KEY
    envVars:
      - name: QUICKLRC_API_KEY

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill sends user-supplied audio/video URLs and optional lyrics to QuickLRC, but the description and usage guidance do not clearly warn users that this content is transmitted to a third-party service. This creates a privacy and data-handling risk because users may provide sensitive media URLs or copyrighted/private lyrics without understanding they leave the local environment.

Content

No source excerpt is available for this finding.