AI agents use vibekit_set_env to create or update resources in Vibekit — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Vibekit environment.
This tool modifies application configuration by setting environment variables. While reversible (variables can be updated or cleared), it has high severity because environment variables often control sensitive settings (API keys, database credentials, feature flags, security policies). Misuse could compromise application security, expose secrets, disable safety controls, or alter critical application behavior.
From the tool's definition Tool description states 'Set one or more environment variables for a hosted app' — this creates or modifies configuration data (environment variables) that affects app behavior.
Attacks that exploit this kind of access
Set one or more environment variables for a hosted app. Changes take effect on next restart. It is categorised as a Write tool in the Vibekit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Vibekit MCP server in PolicyLayer and add a rule for vibekit_set_env: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Vibekit. Nothing to install.
vibekit_set_env is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the vibekit_set_env rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for vibekit_set_env. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
vibekit_set_env is provided by the Vibekit MCP server (vibekit-apps/vibekit-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →