Skip to content
Fencer Vulns
low 3.1

CVE-2023-37275 json

System logs spoofable in Auto-GPT via ANSI control sequences

published 2023-07-13 3 y ago modified 2026-06-17 4 mo ago also EUVD-2023-41186

cvss
3.1
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.4%
EPSS 0.4% chance of exploitation in 30 days, percentile 38%
public exploits
0
none known

Summary

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.

Patch / fix

  • agpt autogpt_classic 0.4.3

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
partial
Assessed
2 y ago

Exploit prediction

0.44% chance of exploitation in the next 30 days, higher than 38% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by version score vector
CNA 3.1 3.1 CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:L/A:N
NVD 3.1 4.3 CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:L/A:N

Affected products

  • Significant-Gravitas Auto-GPT

Classification

Weakness
  • CWE-117 Improper Output Neutralization for Logs

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.