emaillistverify-automation

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

• Third-party content exposure detected (high risk: 0.90). The skill requires calling RUBE_SEARCH_TOOLS against the external Rube MCP (https://rube.app/mcp) / Composio toolkit endpoints to fetch live tool schemas, recommended execution plans, and pitfalls, meaning the agent will ingest and act on untrusted third-party content that can influence tool selection and execution.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires connecting to the Rube MCP runtime endpoint https://rube.app/mcp and calls RUBE_SEARCH_TOOLS/RUBE_MANAGE_CONNECTIONS at runtime to fetch tool schemas and recommended execution plans that directly drive agent instructions, making this external URL a required dependency that controls behavior.