vercel-automation
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from Vercel deployment and runtime logs, creating an attack surface where instructions embedded in logs could influence the agent's behavior.
- Ingestion points: Deployment and runtime logs accessed via
VERCEL_GET_DEPLOYMENT_LOGSandVERCEL_GET_RUNTIME_LOGSinSKILL.md. - Boundary markers: The instructions do not specify any delimiters or warnings to ignore instructions within the ingested data.
- Capability inventory: The skill possesses high-privilege capabilities including
VERCEL_ADD_ENVIRONMENT_VARIABLE,VERCEL_CREATE_NEW_DEPLOYMENT, andVERCEL_CREATE_DNS_RECORD. - Sanitization: No sanitization or validation steps are defined for the logs before they are processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill requires connecting to an external MCP server endpoint at
https://rube.app/mcpto provide its automation tools.
Audit Metadata