vercel-automation
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from external Vercel sources, creating a surface for indirect prompt injection.
- Ingestion points: Data enters the agent context through tools like
VERCEL_GET_DEPLOYMENT_LOGS,VERCEL_GET_RUNTIME_LOGS,VERCEL_GET_DEPLOYMENT_EVENTS, andVERCEL_LIST_PROJECTS(in SKILL.md). - Boundary markers: The instructions do not define clear delimiters or markers to separate untrusted data from system instructions.
- Capability inventory: The skill possesses high-privilege capabilities including managing DNS records (
VERCEL_CREATE_DNS_RECORD), environment variables (VERCEL_ADD_ENVIRONMENT_VARIABLE), and deployments (VERCEL_CREATE_NEW_DEPLOYMENT). - Sanitization: No explicit sanitization or validation steps are provided for the data retrieved from the Vercel API.
- [EXTERNAL_DOWNLOADS]: The skill directs the user to connect to an external MCP server at
https://rube.app/mcpto fetch tool schemas and manage Vercel connections. This represents a dependency on an external infrastructure for the skill's core functionality.
Audit Metadata