dropbox-sign-automation

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

• Third-party content exposure detected (high risk: 0.90). This skill instructs the agent to call external Rube MCP endpoints (e.g., RUBE_SEARCH_TOOLS / RUBE_GET_TOOL_SCHEMAS via https://rube.app/mcp and composio.dev) to fetch tool slugs, input schemas and execution plans which are third-party, potentially untrusted content the agent must read and act on, enabling indirect prompt injection.