Podcast Workflow

Security checks across malware telemetry and agentic risk

Overview

This is a coherent podcast post-production helper, with a clear caution that episode URLs may be fetched over the network.

Install only if you want a full podcast production workflow. Use pasted transcripts or public episode URLs, and avoid private company links, localhost/internal URLs, paywalled content, or confidential transcripts unless you are comfortable with your agent fetching and processing that content.

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 (2)

Missing User Warnings

Low

Confidence: 90% confidence
Finding: The README encourages users to paste episode URLs and explicitly states that the skill 'handles the rest,' but it does not disclose that this likely triggers automatic remote fetching and processing of third-party content. That omission can mislead users about privacy, network access, and data-handling behavior, increasing the chance they submit sensitive internal URLs or content without informed consent.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The skill instructs the agent to fetch arbitrary user-supplied URLs with curl, but it does not require user consent or impose any destination restrictions. This creates a real risk of unintended network access, including requests to internal or sensitive endpoints (SSRF-style behavior), as well as privacy issues from contacting third-party URLs without clear disclosure.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal