- Vulnerability/
- ZDI-CAN-22660
ZDI-CAN-22660: ZDI-23-1772: (0Day) OpenAI ChatGPT Improper Input Validation Model Policy Bypass Vulnerability
First published: Wed Dec 13 2023(Updated: )
This vulnerability allows remote attackers to bypass policy restictions on affected versions of OpenAI ChatGPT. Authentication is required to exploit this vulnerability. The ZDI has assigned a CVSS rating of 6.5.
| Affected Software | Affected Version | How to fix |
|---|---|---|
| OpenAI API |
Never miss a vulnerability like this again
Sign up to SecAlerts for real-time vulnerability data matched to your software, aggregated from hundreds of sources.
Reference Links
Frequently Asked Questions
What is the severity of ZDI-CAN-22660?
The severity of ZDI-CAN-22660 is rated at 6.5 on the CVSS scale.
What does ZDI-CAN-22660 allow attackers to do?
ZDI-CAN-22660 allows remote attackers to bypass policy restrictions on affected versions of OpenAI ChatGPT.
Is authentication required to exploit ZDI-CAN-22660?
Yes, authentication is required to exploit the ZDI-CAN-22660 vulnerability.
Which software is affected by ZDI-CAN-22660?
The affected software for ZDI-CAN-22660 is OpenAI ChatGPT.
How can organizations mitigate ZDI-CAN-22660?
Organizations should ensure they apply any available patches and updates to OpenAI ChatGPT to mitigate ZDI-CAN-22660.
- collector/zdi-published
- alias/ZDI-CAN-22660
- agent/severity
- agent/event
- agent/last-modified-date
- agent/first-publish-date
- agent/references
- agent/title
- agent/type
- agent/description
- agent/softwarecombine
- agent/tags
- agent/guess-ai
- agent/software-canonical-lookup
- agent/software-canonical-lookup-request
- vendor/openai
- canonical/openai api