Ai Podcast Creation

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent podcast-generation helper, but it relies on an external CLI and hosted AI services that may receive user-provided scripts or documents.

Install only if you are comfortable trusting the inference.sh CLI installer, logging into an inference.sh account, and sending podcast prompts, scripts, and any pasted documents to hosted providers such as inference.sh/OpenRouter. Avoid secrets, regulated data, or confidential documents unless that sharing is approved.

SkillSpector

By NVIDIA
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 (1)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill includes workflows that send user-provided text and entire document contents to remote services, including third-party model endpoints, without an explicit warning or consent cue. This creates a real privacy and data-handling risk because users may paste sensitive, proprietary, or regulated content believing processing is local or otherwise undisclosed.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal