AI agents call list_codex_envs to retrieve information from Openai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves configuration and metadata about Codex environments without modifying or executing anything. However, severity is elevated to 'medium' rather than 'low' because the returned information includes network access details and repository references, which could be sensitive configuration data that an agent could misuse to understand attack surface or pivot points if the agent is compromised or…
From the tool's definition Tool name 'list_codex_envs' and description 'Return Codex environments' indicate a retrieval operation. The verb 'Return' and action of listing environments (label, repos, network access) are informational queries with no modification or execution.
Attacks that exploit this kind of access
Return Codex environments (label, repos, network access). It is categorised as a Read tool in the Openai MCP Server, which means it retrieves data without modifying state.
Register the Openai MCP server in PolicyLayer and add a rule for list_codex_envs: 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 Openai. Nothing to install.
list_codex_envs is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_codex_envs 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 list_codex_envs. 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.
list_codex_envs is provided by the Openai MCP server (robotlearning123/gpt2agent). 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 →