Canva Automation

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do what it claims: automate Canva through an external Rube MCP integration, with expected but real third-party content-sharing risks.

Install only if you intend to let the agent use an external Rube MCP connection to operate on your Canva content. Do not provide private, internal, signed, or sensitive asset URLs unless you mean to share that content through Canva/Rube, and treat generated export download links like secrets.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill instructs users to upload assets by public URL but does not warn that the provided URL and referenced content will be transmitted to Canva via an external integration. This can lead users to unintentionally disclose sensitive internal links, signed URLs, or private content to third-party services, especially if they assume the action is local or metadata-only.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The export workflow describes creating exports and retrieving download URLs but does not disclose that design content is processed by Canva and exposed through generated downloadable links. Users may export sensitive designs without understanding that externally accessible URLs are created and that anyone with the link may access the exported data until expiration or revocation.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal