canva-export

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill instructions and logic are consistent with the legitimate task of exporting Canva designs and do not contain malicious patterns.
  • [EXTERNAL_DOWNLOADS]: The skill initiates downloads of exported design files from Canva's official infrastructure, which is a standard part of the service's functionality.
  • [COMMAND_EXECUTION]: Local Python scripts are executed via Bash to interact with the Canva API and manage files. This is standard behavior for this type of tool integration.
  • [PROMPT_INJECTION]: A potential surface for indirect prompt injection is present because the skill processes design and folder names from Canva.
  • Ingestion points: Metadata is retrieved from the Canva API through scripts like list_designs.py.
  • Boundary markers: No explicit delimiters for external metadata are specified in the instructions.
  • Capability inventory: The skill uses Bash to run scripts and Write to save files.
  • Sanitization: The documentation does not describe specific sanitization for design names or other retrieved metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 12:44 AM
Security Audit — agent-trust-hub — canva-export