ClawHub
Back to skill

Security audit

Viral Video Studio

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed short-video workflow that may download and process user-provided video links, but the behavior fits its stated purpose.

Install only if you are comfortable with the agent fetching video URLs you provide, running local media tools, and creating temporary files. Review URLs before analysis, use trusted installs of yt-dlp and ffmpeg, and avoid copying unsafe or unlawful content themes into real posts.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The invocation criteria are very broad and can cause the skill to trigger on generic requests about virality, channel growth, or content strategy, even when the user did not ask for URL downloading, reverse engineering, or monetization workflows. Over-broad activation increases the chance of unexpected tool use, unsolicited network access, and unintended processing of user-supplied links.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs downloading a user-provided URL, extracting media, and writing artifacts into /tmp without any disclosure or confirmation step. This is dangerous because it can lead to silent external network requests, local file creation, and processing of potentially sensitive or malicious URLs without informed user consent.

Missing User Warnings

Medium
Confidence
71% confidence
Finding
The template includes criminal-themed and other potentially problematic example scenarios without any safety framing, which can normalize or steer users toward generating unlawful or harmful-themed content. While the skill is aimed at viral video ideation rather than crime facilitation, including such examples in a copy-paste prompt library creates avoidable downstream misuse and moderation risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal