CVE-2023-37275

MEDIUMCVSS 4.3/10EPSS 0.38%

Last modified

CVE-2023-37275 is a medium-severity vulnerability rated 4.3/10 on the CVSS scale. Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. The Auto-GPT command line UI makes heavy use of color-coded print statements to signify different types of system messages to the user, including messages that are crucial for the user to review and control which commands should be executed. EPSS estimates a 0.38% chance of exploitation in the next 30 days.

Description

Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. The Auto-GPT command line UI makes heavy use of color-coded print statements to signify different types of system messages to the user, including messages that are crucial for the user to review and control which commands should be executed. Before v0.4.3, it was possible for a malicious external resource (such as a website browsed by Auto-GPT) to cause misleading messages to be printed to the console by getting the LLM to regurgitate JSON encoded ANSI escape sequences (`\u001b[`). These escape sequences were JSON decoded and printed to the console as part of the model's "thinking process". The issue has been patched in release version 0.4.3.

Metrics

CVSS 3.1
4.3/10

CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:L/A:N

EPSS Probability
0.38%

29.9th percentile

Probability of exploitation in the next 30 days. Learn more

Weakness Enumeration

Affected Software

VendorProductVersions
AgptAutogpt Classic< 0.4.3

References

Timeline

Published
Last Modified
Status
Analyzed

Frequently Asked Questions

What is CVE-2023-37275?
Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. The Auto-GPT command line UI makes heavy use of color-coded print statements to signify different types of system messages to the user, including messages that are crucial for the user to review and control which commands should be executed. Before v0.4.3, it was possible for a malicious external resource (such as a website browsed by Auto-GPT) to cause misleading messages to be printed to the console by getting the LLM to regurgitate JSON encoded ANSI escape sequences (`\u001b[`). These escape sequences were JSON decoded and printed to the console as part of the model's "thinking process". The issue has been patched in release version 0.4.3.
How severe is CVE-2023-37275?
CVE-2023-37275 has a CVSS score of 4.3/10 (MEDIUM severity). The EPSS model estimates a 0.38% probability of exploitation in the next 30 days.
How do I fix CVE-2023-37275?
Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.

Are you affected by CVE-2023-37275?

Run a free Strix scan to check your systems for this vulnerability.

Scan your code now

Source: NVD / NIST