-21risk-automation

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

• Potentially malicious external URL detected (high risk: 1.00). The skill requires connecting at runtime to the external MCP endpoint https://rube.app/mcp to discover and invoke Composio tools (via RUBE_SEARCH_TOOLS / RUBE_MULTI_EXECUTE_TOOL), which executes remote tool code and can directly control agent behavior.