ClawHub

Editor Ai Best

Security checks across malware telemetry and agentic risk

Overview

This cloud video-editing skill appears functional, but it should be reviewed because it can auto-connect to NemoVideo and broadly send prompts or media to remote processing without a clear consent step.

Review before installing. Use it only if you are comfortable sending selected videos, prompts, session metadata, and related files to NemoVideo.ai for cloud processing; avoid confidential footage unless you trust that provider, and instruct the agent to ask before connecting, uploading, editing, or exporting.

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
89% confidence
Finding
The onboarding and invocation phrases are broad enough to match normal conversation, which can cause the skill to activate unexpectedly and begin handling user content without a clearly intentional trigger. In this skill, that risk is amplified because activation can lead to automatic backend connection and later remote media upload/processing, increasing the chance of unintended data transfer or confusing user consent boundaries.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill instructs the agent to automatically connect to an external backend, obtain or use tokens, and process user media remotely, but it does not require a prominent user-facing disclosure or consent flow before data is transmitted. Because this skill handles raw video footage, session identifiers, and authentication tokens for a third-party service, the lack of explicit warning makes unintended disclosure of potentially sensitive media and metadata substantially more dangerous.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal