visme-automation

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill configures the agent to use an external Model Context Protocol (MCP) server at https://rube.app/mcp. This server provides the tool definitions and logic for Visme automation. This is a standard integration for the Composio service.
  • [COMMAND_EXECUTION]: Provides capabilities to execute various Visme operations (e.g., project management, design tasks) through the RUBE_MULTI_EXECUTE_TOOL command, which interfaces with the remote MCP backend.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by processing data from an external provider.
  • Ingestion points: Tool schemas and execution results are fetched from the remote server via RUBE_SEARCH_TOOLS and RUBE_MULTI_EXECUTE_TOOL in the SKILL.md workflows.
  • Boundary markers: No specific delimiters or safety instructions are defined in the skill to isolate tool outputs from the agent's control flow.
  • Capability inventory: Includes tool execution via RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH.
  • Sanitization: Relies on the host agent's internal filtering and the MCP server's input validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 07:09 AM