ClawHub

podcast-highlights-deck

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: it helps build a podcast highlights website, while using expected downloads, transcription, audio clipping, and site-generation tools.

Install only if you are comfortable with the agent downloading podcast media, creating local audio/transcript/site files, and using trusted media/transcription tools. For private or sensitive recordings, confirm whether transcription will run locally or be sent to a third-party provider before using the skill.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill directs the agent to read and write local files and execute shell commands (`yt-dlp`, `ffmpeg`, Python scripts, site build steps) but does not declare permissions or boundaries for those capabilities. This is dangerous because hidden or undeclared execution and filesystem access reduces user visibility and weakens policy enforcement, increasing the chance of unintended file modification or command execution beyond the expected task.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The workflow instructs the agent to download episode audio and create multiple artifacts (`episode.mp3`, transcripts, clipped audio, bundled site files) without any disclosure to the user that local files will be created and modified. This is risky because users may not expect persistent storage, large downloads, or overwriting of existing workspace content, which can cause privacy, storage, and integrity issues.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill instructs use of web fetching plus external transcription/downloading services, including RSS retrieval, possible `yt-dlp` use, and Whisper/OpenAI fallback, without warning that podcast audio, URLs, and metadata may be transmitted to third parties. This creates privacy and compliance risk because even publicly accessible media can still carry sensitive user intent, tracking data, or copyrighted content handling implications when sent to external services.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal