Back to skill

Security audit

Phy Video Bgm

Security checks across malware telemetry and agentic risk

Overview

The skill does what it claims, but it should be reviewed because it can upload user videos to external AI services, remove original audio in outputs, and build shell commands from user-controlled values without clear validation guidance.

Install only if you are comfortable with video content or derived prompts being sent to Google Gemini and fal.ai using your API keys. Keep original videos backed up, verify output filenames, and avoid untrusted values for speed, volume, fade, style, or paths until the skill adds explicit confirmation and input validation.

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 (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger text is broad enough to activate on nearly any request to add music to a video, increasing the chance the skill runs without the user understanding that it will upload media to third-party AI services and replace/remove existing audio. In this context, overbroad activation is risky because the skill performs consequential actions on user content rather than a local, read-only transformation.

Missing User Warnings

High
Confidence
98% confidence
Finding
The skill description does not clearly warn that video content is sent to Gemini/fal.ai and that FFmpeg removes the original audio track before creating a new output. This creates a meaningful privacy and integrity risk because users may expose sensitive video content to third parties or unintentionally overwrite the video's original sound design.

VirusTotal

No VirusTotal findings

View on VirusTotal