Back to skill

Security audit

audiobooklm-podcast

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward audiobook and podcast production workflow that uses a disclosed Ximalaya MCP service and requires user confirmation before creation, synthesis, mixing, or publishing actions.

Install this only if you intend to connect an account token for the Ximalaya audiobook creation service. Expect your scripts, book/chapter metadata, generated audio tasks, and optional album uploads to be handled by that service; confirm publishing and any payment/recharge steps manually.

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

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.