OpenAI patents system that hides passwords from AI agents
OpenAI describes a method for letting AI agents use external services without seeing the actual login passwords. The system swaps real credentials for fake placeholders that the AI can use to make requests, while the real passwords stay hidden in a secure vault.
In the filing’s own words
This disclosure describes systems and methods for securely mediating access by generative artificial intelligence (AI) agent to external services without exposing sensitive credentials to the generative AI agent. The disclosed systems can store sensitive credentials within a secret store inaccessible to the generative model agent, generate opaque placeholder credentials bound to designated domains and request constraints, and inject the opaque placeholder credentials into the generative agent environment. The disclosed systems can intercept requests from the generative agent environment containing the opaque placeholder credentials, verify that the requests satisfy domain and request constraints, and replace the opaque placeholder credentials with cryptographic credentials derived from the sensitive credentials. The disclosed systems can provide the regenerated requests to external services and return outputs from the external services to the generative agent environment.
What exactly they claim (claim 1)
1. A computer-implemented method comprising: determining, based on input from a client device, agent configuration data defining a generative agent environment that uses an external service to perform operations, the agent configuration data indicating a sensitive credential, a classification of the sensitive credential, and a designated domain; generating, from the sensitive credential, an opaque placeholder credential indicating the designated domain and replacing the sensitive credential with a unique reference to the sensitive credential according to a format corresponding to the classification of the sensitive credential; injecting the opaque placeholder credential into the generative agent environment for use by a generative model agent operating in the generative agent environment; and executing an operation within the generative agent environment by using the generative model agent to call the external service using the opaque placeholder credential.
Facts
- Company
- OpenAI (OpenAI OpCo, LLC)
- Official title
- Obfuscating and mediating sensitive credentials for generative agent environments
- Patent number
- US12783730B1
- Application number
- 19562153
- Filed
- Mar 10, 2026
- Granted
- Nov 3, 2026
- Inventors
- 3
- Claims
- 20
Classified under
G06F 21/6254 Physics & computingH04L 9/0825 Electricity & electronicsH04L 9/3213 Electricity & electronicsMore from OpenAI in Security & privacy
- OpenAI patents AI agents that scan code changes for security flaws Nov 5, 2026
- OpenAI patents AI agents that find security flaws in code Nov 5, 2026
- OpenAI patents AI system to find security flaws in computer code Nov 5, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.
