Ai Video Editor Enhancer

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:38 PM UTC
• Version:
  1.0.0

Overview

This is a cloud video-editing skill whose remote media processing is disclosed and fits its stated purpose, though users should treat uploaded media as shared with the provider.

Install only if you are comfortable sending selected videos, images, audio, URLs, and editing prompts to NemoVideo's cloud service. Do not upload confidential, regulated, or private footage unless you trust the provider's retention and privacy practices, and keep any NEMO_TOKEN private.

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
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Description-Behavior Mismatch

Medium

• Confidence: 96% confidence
• Finding: The skill is presented as a simple video enhancer, but the implementation exposes materially broader capabilities including timeline inspection, text/audio manipulation, state querying, and export orchestration. This mismatch can mislead users and host systems about the true permission and data-handling scope, increasing the risk of unintended actions on user media and reducing informed consent.

Description-Behavior Mismatch

Medium

• Confidence: 97% confidence
• Finding: The skill markets itself as accepting local raw video uploads, yet the documented API also supports remote URL ingestion and multiple non-video media types. Hidden expansion of accepted inputs can enable unexpected external fetching, broaden attack surface, and cause users to disclose or process content they did not expect the skill to handle.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: Routing nearly all unmatched requests to the SSE action creates an overly permissive execution path for arbitrary user text. In this skill, that broad fallback can send unintended prompts and editing commands to a remote backend with session context, increasing the likelihood of unexpected operations, data disclosure, or abuse of backend capabilities beyond the user's intent.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The getting-started and marketing text does not clearly warn users that uploaded videos and instructions are sent to a third-party cloud processing backend. For a media skill handling potentially sensitive footage, lack of prominent disclosure undermines informed consent and can expose personal, confidential, or regulated content to remote services unexpectedly.

VirusTotal

66/66 vendors flagged this skill as clean.