ClawHub

Video Compressor Ai

Security checks across malware telemetry and agentic risk

Overview

This is a cloud video-compression skill whose network, token, upload, and export behavior fits its stated purpose, but users should understand their videos may be sent to nemovideo.ai.

Install only if you are comfortable sending video files, URLs, prompts, and processing metadata to the nemovideo.ai cloud backend. Avoid confidential or regulated footage unless you trust that provider’s handling practices, use a limited NEMO_TOKEN where possible, and monitor credit or subscription usage.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

Medium
Confidence
89% confidence
Finding
The skill instructs the agent to obtain anonymous service tokens and use remote account/credit functionality even when the user has not explicitly consented to external service authentication. This broadens the skill from local advice/compression assistance into silent third-party service access, which can create unanticipated account creation, credit consumption, tracking, and policy bypass risks.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill directs the agent to connect to an external backend, use authentication material, and create sessions before handling requests, but it does not require informing the user that data will be sent off-platform or that credits/accounts may be affected. This is dangerous because users may disclose sensitive video metadata or content under the assumption of local processing when the skill is actually performing networked operations with billing implications.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill supports uploading local files or remote URLs to a cloud API and exporting processed media, yet it provides no clear warning about privacy, retention, third-party processing, or the sensitivity of the uploaded media. For a video tool, this is especially risky because videos commonly contain faces, voices, locations, internal training material, or other confidential content that could be exposed through unintended remote transfer.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal