ClawHub

Podcast Agent

Security checks across malware telemetry and agentic risk

Overview

This skill behaves like a disclosed podcast generator: it searches or fetches articles, creates scripts, and sends script text to Edge TTS to make MP3 files.

Install only if you are comfortable with an unpinned Python TTS dependency, outbound web fetching, and sending podcast script text to the Edge TTS provider. Avoid private or regulated content, and give explicit source or duration limits for topics where accuracy matters.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The example trigger phrase is broad natural language that could overlap with ordinary user conversation, making accidental or overbroad activation more likely. In a skill that performs web search, content fetching, script generation, and audio synthesis, ambiguous invocation can lead to unintentional network activity, content processing, and file creation without clear user intent.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The user interaction section says the agent will automatically search, read articles, generate a script, synthesize audio, and send an MP3 based on a generic request, without clear boundaries or approval gates. This ambiguity increases the risk of unintended autonomous actions, especially because the workflow includes network access and local file output that may be triggered from common user requests.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal