Back to skill

Security audit

canva

Security checks across malware telemetry and agentic risk

Overview

This skill is a Canva design-workflow guide with disclosed, purpose-aligned use of Canva connectors and human review before publishing.

Installers should understand that this skill can guide an agent to create, resize, or adapt Canva designs when Canva connectors are already connected, and to hand finished exports into a publishing workflow. Keep the documented human approval step, verify Canva feature/credit claims in-app, and ensure brand assets, templates, AI imagery, and likenesses are properly licensed before use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.