Image To Video Generator Unrestricted

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:41 PM UTC
• Version:
  1.0.0

Overview

This is an instruction-only image-to-video skill that clearly uses a third-party cloud backend, with no evidence of hidden code execution or unrelated data access.

Install only if you are comfortable sending images, prompts, and possibly media URLs to the Nemo/nemovideo.ai cloud service. Do not upload sensitive or proprietary media unless you trust that service’s retention and privacy practices, and be aware the unexplained ~/.config/nemovideo/ requirement should be clarified by the publisher.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Context-Inappropriate Capability

Medium

• Confidence: 86% confidence
• Finding: Allowing URL-based media ingestion expands the trust boundary from user-uploaded local images to arbitrary remote resources. This can enable server-side fetching of attacker-controlled URLs, potentially exposing the backend to SSRF-like behavior, internal resource access, or unintended retrieval of sensitive network-reachable content if the backend does not strictly validate destinations.

Vague Triggers

Medium

• Confidence: 80% confidence
• Finding: Routing essentially all unmatched requests to the SSE generation action creates an overly permissive execution path that can send unintended user inputs to the remote backend. In practice, this increases the chance of accidental data disclosure, unexpected billable operations, or misuse of the editing pipeline for requests outside the skill's stated image-to-video scope.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill sends user prompts and uploaded media to a third-party cloud backend but does not present a clear, up-front privacy warning in the main user-facing description. This creates a real risk of users unknowingly transmitting sensitive images, text, or metadata off-device to an external service, which is especially concerning for a media-processing skill handling potentially private content.

VirusTotal

65/65 vendors flagged this skill as clean.