ClawHub
Back to skill

Security audit

AutoClip Pro

Security checks across malware telemetry and agentic risk

Overview

This is a real local video-processing skill, but it uses unsafe shell-built FFmpeg commands and includes unrelated promotional playbooks that users should review carefully.

Install only if you trust the publisher and can run it in a limited test folder. Avoid processing untrusted files or filenames with shell metacharacters, review config values before running, and ignore the included social promotion playbooks. A safer version should invoke FFmpeg with argument arrays and shell:false, validate inputs, include a dry-run or confirmation step, and remove the misleading install.bat/run.bat references unless those files are supplied.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

Medium
Confidence
97% confidence
Finding
This module constructs shell command strings from multiple externally influenced values such as file paths, watermark text, subtitle paths, timing options, and configurable ffmpeg/ffprobe paths, then executes them with execSync or spawn using shell enabled. Because shell metacharacters, quotes, and FFmpeg filter syntax can be attacker-controlled, this can lead to OS command injection and arbitrary command execution, which is far more dangerous than normal video processing.

Missing User Warnings

Medium
Confidence
78% confidence
Finding
The skill advertises automatically scanning a folder and batch-processing all videos, but does not document safeguards such as dry-run mode, output-directory isolation, overwrite behavior, or confirmation prompts. In a bulk media workflow, this can lead to unintended modification, replacement, or large-scale processing of user files, increasing the blast radius of mistakes or misuse.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
scripts/video-editor.js:29