Image To Video In Free

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:39 PM UTC
• Version:
  1.0.0

Overview

This is a disclosed cloud image-to-video skill, with the main caution that it can contact NemoVideo and send selected media or prompts to that service.

Install only if you are comfortable sending chosen images, prompts, media URLs, draft state, and export requests to NemoVideo. Use a dedicated NEMO_TOKEN where possible, avoid confidential or regulated media, and ask the agent to confirm before uploading or exporting when your request is ambiguous.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• 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
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The invocation examples are short, generic phrases like "export 1080p MP4" and "turn my photos into a short," which creates a real risk of accidental activation in unrelated conversations. In an agent that performs automatic setup and external API calls, broad trigger language can cause unintended network actions or media-processing workflows without sufficiently clear user intent.

Vague Triggers

Medium

• Confidence: 96% confidence
• Finding: The catch-all rule routes "Everything else" into SSE generation/edit actions, which is overly permissive and can interpret unrelated user text as commands to a remote backend. Because SSE is the main action path and may modify session state or trigger processing, this broad fallback increases the chance of unintended external requests and state changes.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill directs the agent to automatically connect to an external service, generate an anonymous token, and create a session "before doing anything else," without first obtaining user consent or clearly disclosing that data will be sent to a third-party API. This is dangerous because it can initiate network activity and establish an external session prior to informed user approval, especially in a workflow involving user-uploaded images.

VirusTotal

66/66 vendors flagged this skill as clean.