ClawHub

Image To Video Ai Generator Free Online

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed cloud image-to-video skill, but users should treat uploaded media and prompts as being sent to NemoVideo’s remote service.

Install only if you are comfortable sending images, audio, video, prompts, and project state to the NemoVideo cloud API. Avoid confidential or rights-sensitive media unless you trust that provider, and confirm before uploads or exports because the skill can create sessions and use credits.

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
91% confidence
Finding
The trigger phrases are extremely generic, such as 'export' or 'convert my still images', making accidental activation likely during ordinary conversation. In an agent setting, broad activation can cause unintended uploads, session creation, or remote API calls involving user media and prompts without sufficiently deliberate consent.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The catch-all rule routing 'Everything else' to the SSE generation path is overly broad and can interpret unrelated user language as instructions for the remote backend. This raises the risk of unintended data transmission, external processing, and costly or privacy-impacting operations from ambiguous conversational input.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to connect to a cloud backend, create anonymous tokens, and process user media remotely, but it does not prominently warn users that their uploads and prompts are being transmitted off-device. This creates a meaningful privacy and consent issue, especially for personal images or sensitive media.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal