canva-automation
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Canva that could contain malicious instructions.
- Ingestion points: Data is ingested via
CANVA_LIST_USER_DESIGNS(design titles/metadata) andCANVA_ACCESS_USER_SPECIFIC_BRAND_TEMPLATES_LIST(template names and placeholders). - Boundary markers: There are no explicit instructions or delimiters mentioned to isolate these data points from the agent's command logic.
- Capability inventory: The skill possesses the capability to perform network fetches via
CANVA_CREATE_ASSET_UPLOAD_JOB(using a URL) and trigger design exports viaCANVA_CREATE_CANVA_DESIGN_EXPORT_JOB. - Sanitization: No sanitization or validation of the ingested metadata is described before it is used in subsequent tool sequences.
- [EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external MCP server located at
https://rube.app/mcp. This server provides the underlying tool schemas and execution logic for the Canva integration.
Audit Metadata