canva-explorer
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes local Python scripts within a virtual environment to interact with the Canva API. These operations are limited to discovery and do not modify account data.
- [PROMPT_INJECTION]: The skill processes design and folder metadata from an external source (Canva), which introduces a surface for indirect prompt injection.
- Ingestion points: Data retrieved via list_designs.py, get_design.py, and search_designs.py.
- Boundary markers: No delimiters or ignore-instructions warnings are defined.
- Capability inventory: Execution of local scripts and file write permissions for logging results.
- Sanitization: The instructions do not specify any validation or sanitization of the retrieved metadata.
Audit Metadata