outlook-automation

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses Composio/Rube MCP Outlook tools to search/query/get emails and attachments, which at runtime will ingest outsider-authored email body text and attachment contents into the agent’s LLM context (indirect prompt injection risk via message/attachment text).

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires adding and using the MCP endpoint https://rube.app/mcp at runtime and instructs calling RUBE_SEARCH_TOOLS to fetch current tool schemas, so remote content from that URL directly controls the agent's tool schemas and behavior.