For Marketing Editor Ai

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:37 PM UTC
• Version:
  1.0.0

Overview

This is a cloud video-editing skill whose network calls, token use, uploads, and exports match its stated purpose, with privacy cautions for uploaded media.

Install only if you are comfortable sending video files, media URLs, edit prompts, and a NemoVideo token or anonymous session token to mega-api-prod.nemovideo.ai. Avoid confidential footage or internal/private URLs unless you trust that service’s privacy, retention, and access controls.

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

Low

• Confidence: 87% confidence
• Finding: The skill’s public description frames input as user-uploaded local footage, but the documented upload API also permits arbitrary remote URLs. That creates a broader trust boundary than disclosed and can enable server-side fetching of attacker-controlled resources, with risks such as SSRF-like behavior, unexpected ingestion of sensitive URLs, or downloading untrusted content without clear user awareness.

Vague Triggers

Medium

• Confidence: 85% confidence
• Finding: The invocation guidance is broad and generic, making it easier for unrelated user messages to activate the skill unintentionally. In a skill that uploads media and connects to an external backend, over-broad triggering can cause unintended data transfer or backend actions without sufficiently clear user intent.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The catch-all routing rule sends 'everything else' to the SSE action, which is an overly permissive dispatch mechanism. Because SSE appears to drive editing commands to a remote backend, ambiguous routing can cause unintended remote processing of arbitrary user text and increase the chance of prompt/command confusion or accidental job execution.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The skill description does not clearly warn users that uploaded footage is sent to a third-party cloud backend for processing. Since videos may contain sensitive personal, corporate, or unpublished marketing material, omission of this disclosure increases privacy and data-handling risk and can undermine informed consent.

VirusTotal

66/66 vendors flagged this skill as clean.