front-automation
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
- EXTERNAL_DOWNLOADS (LOW): The skill requires the configuration of an external MCP server endpoint (https://rube.app/mcp). This service is not on the pre-approved trusted sources list and dynamically provides the tool schemas and execution logic used by the agent.
- DATA_EXFILTRATION (LOW): The skill facilitates access to the Front platform, which typically contains sensitive customer communications and internal business data. The use of a third-party MCP intermediary (Rube/Composio) requires trust in the external service's data handling practices.
- INDIRECT_PROMPT_INJECTION (LOW): * Ingestion points: Data ingested from Front (emails, messages, tickets) via the toolkit. * Boundary markers: None specified in the instructions to prevent the agent from following instructions embedded in emails. * Capability inventory: The agent can execute multiple tools (RUBE_MULTI_EXECUTE_TOOL) and perform workbench tasks, which could be abused if malicious instructions are processed. * Sanitization: No evidence of sanitization or escaping of incoming message content is provided.
Audit Metadata