Ai Voiceover Canva

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

Overview

This skill is a disclosed cloud AI voiceover workflow, but it sends user media and prompts to NemoVideo for processing.

Install only if you are comfortable sending Canva exports, PDFs, images, videos, URLs, prompts, and render state to NemoVideo's cloud service under a NEMO_TOKEN. Avoid confidential or regulated material unless you trust that provider's privacy, retention, and quota handling, and use the skill only for intentional voiceover or video-editing tasks.

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 (3)

Description-Behavior Mismatch

Medium

• Confidence: 91% confidence
• Finding: The manifest markets a narrow Canva voiceover workflow, but the body documents a much broader remote editing, upload, state inspection, and rendering pipeline. This capability mismatch can mislead users and host systems about what the skill is authorized to do, increasing the chance of unexpected remote processing of arbitrary media and edits beyond the declared purpose.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The routing rule sends 'Everything else' to the SSE action, creating an overly broad trigger that may capture unrelated user requests. In a skill with remote upload/edit/export abilities, this can cause unintended invocation, accidental data transfer, or edits on user media when the user did not clearly intend to use this skill.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The onboarding text encourages users to send files but does not clearly warn up front that uploaded media is transmitted to a third-party cloud backend for processing. Because the skill handles user-provided videos, images, and PDFs, inadequate disclosure can lead to privacy violations, accidental sharing of sensitive content, and noncompliant data handling.

VirusTotal

64/64 vendors flagged this skill as clean.