ClawHub
Back to skill

Security audit

Video Ai Process

Security checks across malware telemetry and agentic risk

Overview

This video-processing skill has a coherent purpose, but it needs review because it can send video-derived data to Feishu automatically and contains an unsafe shell command path.

Review before installing or running. Use only trusted local video paths, avoid confidential videos unless Feishu and MiniMax handling is approved, mask Feishu values in logs, and require explicit confirmation before remote writes, heartbeat polling, or generated media persistence.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill explicitly describes sending video-derived summaries, file paths, source filenames, timestamps, and other metadata to Feishu, but it does not clearly require informed user consent or prominently warn that processed content leaves the local environment. This creates a real privacy and data-governance risk, especially if videos contain sensitive business, personal, or regulated information.

Missing User Warnings

Medium
Confidence
85% confidence
Finding
The skill documents automatic creation of composed video files and automatic writing of records to Feishu immediately after processing, but does not present this as a high-visibility consented side effect. Automatic file creation and external record publication can surprise users, expose sensitive derived media, and cause unintended persistence of data.

Missing User Warnings

Medium
Confidence
99% confidence
Finding
The script interpolates a user-controlled video path into a shell command and executes it with shell=True. An attacker can supply crafted shell metacharacters or quoting-breaking input to execute arbitrary commands with the privileges of the script, making this substantially dangerous in a pipeline that accepts external file paths.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.