ClawHub

Opusclip

Security checks across malware telemetry and agentic risk

Overview

This cloud video-clipping skill is purpose-aligned, but its broad automatic routing could send prompts or media to NemoVideo without clear user confirmation.

Install only if you are comfortable sending selected videos, prompts, and related session data to mega-api-prod.nemovideo.ai. Use explicit OpusClip requests, avoid sensitive or regulated media unless you have verified the vendor's privacy and deletion policies, and consider requiring confirmation before token creation, session creation, uploads, or SSE edit requests.

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 (3)

Vague Triggers

Medium
Confidence
83% confidence
Finding
The invocation examples are broad enough that ordinary conversation could unintentionally activate the skill and initiate backend setup or token acquisition. In this skill, activation is more sensitive because it can automatically connect to a cloud service and process user media, creating consent and privacy risks.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The catch-all routing rule sends 'everything else' to the SSE editing path, which makes accidental activation highly likely. Because this path can transmit prompts to a remote backend and potentially act on session state, ambiguous routing increases the chance of unintended data disclosure or unwanted actions.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill does not prominently warn that user prompts, uploaded videos, and related session data are sent to a third-party cloud backend for processing. This is dangerous because users may share sensitive media or confidential prompts without informed consent, and the skill also auto-connects to the backend on first open, increasing exposure.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal