canva-automation
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs users to configure an external MCP server located at
https://rube.app/mcp. This server acts as the gateway for interacting with Composio's Canva toolkit and is a necessary dependency for the skill's functionality. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Canva design environments which may contain untrusted content provided by other users or collaborators.
- Ingestion points: Data is brought into the agent context via design listings (
CANVA_LIST_USER_DESIGNS) and brand template lists (CANVA_ACCESS_USER_SPECIFIC_BRAND_TEMPLATES_LIST) as referenced inSKILL.md. - Boundary markers: The instructions do not define specific delimiters or "ignore" directives to prevent the agent from potentially following instructions embedded within design titles, template names, or placeholder values.
- Capability inventory: The skill possesses capabilities for network operations (uploading assets via URL in
CANVA_CREATE_ASSET_UPLOAD_JOB), modifying library structures (CANVA_MOVE_ITEM_TO_SPECIFIED_FOLDER), and generating new designs. - Sanitization: The documentation lacks specific requirements for sanitizing or validating design-related metadata before it is processed by the AI agent.
- [NO_CODE]: The skill package contains no executable scripts or binary files, consisting solely of instructions and configuration metadata in
SKILL.md.
Audit Metadata