canvas-automation

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references an external MCP server endpoint (https://rube.app/mcp) and documentation (https://composio.dev/toolkits/canvas). These are official resources for the Composio platform and are used for standard configuration.
  • [COMMAND_EXECUTION]: The instructions guide the agent to perform operations via specific MCP tools (RUBE_SEARCH_TOOLS, RUBE_MULTI_EXECUTE_TOOL, etc.) to interact with the Canvas API through the Composio service. This is the intended and transparent functionality of the skill.
  • [DATA_EXPOSURE]: The skill manages external account connections via RUBE_MANAGE_CONNECTIONS. It appropriately instructs the user to follow an authentication link for setup, following standard OAuth/integration patterns without exposing credentials within the skill itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 04:01 PM
Security Audit — agent-trust-hub — canvas-automation