ClawHub
Back to skill

Security audit

video-add-b-roll

Security checks across malware telemetry and agentic risk

Overview

This skill performs the disclosed video-editing workflow it describes, with no evidence of hidden exfiltration, destructive behavior, or unrelated authority.

Before installing, be aware that this skill can read a local Pexels API key, contact Pexels, run ffmpeg-based media commands, and modify files under a video project. Use it only on projects where you are comfortable generating durable review, cache, render, and operation metadata.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill performs privileged actions including reading environment variables, reading and writing project files, invoking shell commands, and making network requests to Pexels, but it declares no permissions. That mismatch is dangerous because users or the execution framework may authorize the skill under incomplete assumptions, while the skill can still access secrets like PEXELS_API_KEY and modify repository state and output artifacts.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.