vercel-automation
Warn
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: MEDIUMREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill requires the user to configure an external Model Context Protocol (MCP) server at
https://rube.app/mcp. This third-party service manages the execution of all Vercel platform tools. Connecting production environments to unverified remote servers for high-privilege management represents a security concern.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external deployment and runtime logs that may contain untrusted data.\n - Ingestion points: The agent retrieves log content via tools like
VERCEL_GET_DEPLOYMENT_LOGSandVERCEL_GET_RUNTIME_LOGS.\n - Boundary markers: There are no programmatic boundary markers or explicit instructions to treat log content as data rather than instructions.\n
- Capability inventory: The skill has extensive write access, including the ability to add environment variables (
VERCEL_ADD_ENVIRONMENT_VARIABLE), modify DNS records (VERCEL_CREATE_DNS_RECORD), and trigger new deployments.\n - Sanitization: The skill relies on natural language instructions for the agent to redact personal data rather than implementing strict programmatic sanitization or validation of the log content.
Audit Metadata