remote-retrieval-automation

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill requires connecting to the external Rube MCP endpoint (https://rube.app/mcp) and explicitly mandates calling RUBE_SEARCH_TOOLS to fetch tool slugs, input schemas and recommended execution plans from Composio/Rube toolkits, which are third-party public content that the agent must interpret and which can directly influence subsequent tool invocation and behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The Rube MCP endpoint https://rube.app/mcp is added as a required MCP server and is used at runtime (via RUBE_SEARCH_TOOLS / RUBE_MULTI_EXECUTE_TOOL) to fetch tool schemas and recommended execution plans that directly control how the agent constructs prompts and executes tools, so it is a runtime external dependency that can control agent behavior.