AI agents call custom_instructions_get 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 stored configuration data (custom instructions) from a ChatGPT account without modifying or executing anything. While custom instructions may contain sensitive information about user preferences or workflows, the tool explicitly redacts PII and performs only a query/fetch operation.
From the tool's definition Tool name contains 'get' and description states 'Return ChatGPT custom instructions', indicating data retrieval with no modification or side effects. PII redaction further confirms read-only intent.
Attacks that exploit this kind of access
Return ChatGPT custom instructions (PII redacted). 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 custom_instructions_get: 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.
custom_instructions_get 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 custom_instructions_get 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 custom_instructions_get. 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.
custom_instructions_get 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 →