openai · OpenAI Platform Docs
Safety checks
Explains how to implement safety identifiers to prevent organization-wide bans by attributing high-risk requests to specific end users using the safetyidentifier parameter or OpenAI-Safety-Identifier header.
Derived skill
Files assembled from official documentation
Viewing SKILL.md
Safety checks
Explains how to implement safety identifiers to prevent organization-wide bans by attributing high-risk requests to specific end users using the safetyidentifier parameter or OpenAI-Safety-Identifier header.
When To Use
Use when you need to implement user-level safety tracking to prevent a single malicious user from causing an organization-wide service suspension or ban.
Reference Files
| File | Contains | Use For |
|---|---|---|
SKILL.md | Entry point: scope, routing table, and workflow. | Start here. |
docs/safety-checks-workflow-guide.md | A guide explaining the safety classifier process, error mitigation, and implementation of safety identifiers for GPT-5 and future models. | Questions about a guide explaining the safety classifier process, error mitigation, and implementation of safety identifiers for GPT-... |
examples/safety-checks-openai-safety-checks-python-chat-completions.python | A Python code example demonstrating how to implement safety identifiers within a Chat Completions API request using the OpenAI client. | Exact payloads, commands, or snippets shown in A Python code example demonstrating how to implement safety identifiers within a Chat Completions API request using t... |
examples/safety-checks-openai-safety-checks-chat-completions.curl | A curl command demonstrating how to include safety identifiers in a chat completions request to the OpenAI API. | Exact payloads, commands, or snippets shown in A curl command demonstrating how to include safety identifiers in a chat completions request to the OpenAI API. |
examples/safety-checks-openai-safety-checks-python-client-request.python | A Python code example demonstrating how to use the OpenAI client to create a response with a safety identifier. | Exact payloads, commands, or snippets shown in A Python code example demonstrating how to use the OpenAI client to create a response with a safety identifier. |
examples/safety-checks-openai-api-safety-checks-curl-request.curl | A curl command demonstrating how to send a request to the OpenAI API with safety identifier parameters. | Exact payloads, commands, or snippets shown in A curl command demonstrating how to send a request to the OpenAI API with safety identifier parameters. |
What This Skill Covers
- With the introduction of GPT-5, we added some checks to find and halt hazardous information from being accessed. It's likely some users will eventually try t...
- Main sections:
Safety classifiers for GPT-5 and forward,The safety classifier process,How to avoid errors, latency, and bans,Implementing safety identifiers for individual users,Potential consequences.
Workflow
- Open the most relevant file under
docs/for the exact documented workflow and wording. - Open
schemas/files for exact structured contracts. - Open
examples/files for concrete requests, commands, snippets, and manifests. - Do not add behavior or configuration that is not present in the attached source files.
Canonical source: https://developers.openai.com/api/docs/guides/safety-checks.md
