vercel
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill leverages the
vercelCLI to perform a wide range of actions including deploying code, managing domains, and switching teams. - [INDIRECT_PROMPT_INJECTION]: The skill acts as an interface for managing project data and environment variables, which could be exploited by malicious content within a project.
- Ingestion points: Project source code, configuration files, and environment variable values processed by commands like
vercel,vercel build, andvercel env ls(SKILL.md). - Boundary markers: No specific delimiters or warnings to ignore instructions within project files are defined.
- Capability inventory: The skill can execute deployments, modify project settings, manage domains, and read/write environment variables (SKILL.md).
- Sanitization: The skill does not describe any validation or sanitization mechanisms for the data it processes.
Audit Metadata