Ai Image To Video Editor

• Outcome: Review
• Latest audit: May 29, 2026, 9:33 PM
• Version:
  1.0.0

Overview

This image-to-video skill appears purpose-built rather than malicious, but it needs review because broad prompts and uploads can be sent to a cloud video service without a clear consent gate.

Install only if you are comfortable sending selected images, prompts, timeline/project state, and render jobs to NemoVideo's cloud service. Avoid sensitive personal, client, or proprietary images unless you trust that provider's privacy and retention practices, and require confirmation before upload, generation, export, or credit-consuming actions.

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: 92% confidence
• Finding: The startup prompt and example phrases are broad enough that ordinary user conversation like 'convert my images' or even vague statements about making a video could trigger the skill unexpectedly. In an agent environment, over-broad invocation increases the chance that unrelated user content or attached files are sent to the external video backend without clear, deliberate user consent.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The routing rule sends 'Everything else' to the SSE generation/edit path, which effectively makes the default behavior to forward arbitrary unmatched user input to the remote backend. Because this skill handles uploaded media and persistent sessions, such catch-all routing can cause unintended data disclosure, unwanted edits, or remote actions from ambiguous prompts that were never clearly meant for this tool.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill description emphasizes convenience but does not clearly warn users that their images, prompts, and project state are transmitted to a third-party cloud rendering service. For a media-processing skill, this is a real privacy and consent issue because users may share sensitive or proprietary images assuming processing is local or not realizing remote retention/session state is involved.

VirusTotal

66/66 vendors flagged this skill as clean.