How severe is CVE-2023-37275?

CVE-2023-37275 has a CVSS 3.x base score of 3.1, rated low severity. It is exploitable over network with high attack complexity, requires no privileges and user interaction. Impact on confidentiality is none, integrity low, and availability none.

Is CVE-2023-37275 being actively exploited?

It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (30th percentile), an estimate of the probability of exploitation in the next 30 days.

What products are affected by CVE-2023-37275?

CVE-2023-37275 affects Agpt Autogpt Classic. See the affected-products list for the exact vulnerable versions.

How do I fix CVE-2023-37275?

Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround.

When was CVE-2023-37275 published?

CVE-2023-37275 was published on 2023-07-13 and last updated on 2026-06-17.

CVE-2023-37275

CVE-2023-37275 is a low-severity vulnerability in Agpt Autogpt Classic with a CVSS 3.x base score of 3.1. It is not currently listed as actively exploited by CISA, and its EPSS exploit-prediction score is low. The underlying weakness is classified as CWE-117.

Key facts

Severity: Low (CVSS 3.x base score 3.1)
EPSS exploit prediction: 0% (30th percentile)
Actively exploited: Not listed in CISA KEV
Weakness: CWE-117
Affected product: Agpt Autogpt Classic
Published: 2023-07-13
Last modified: 2026-06-17

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.

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 3.x base score of 3.1, rated low severity. It is exploitable over network with high attack complexity, requires no privileges and user interaction. Impact on confidentiality is none, integrity low, and availability none.
Is CVE-2023-37275 being actively exploited?: It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (30th percentile), an estimate of the probability of exploitation in the next 30 days.
What products are affected by CVE-2023-37275?: CVE-2023-37275 affects Agpt Autogpt Classic. See the affected-products list for the exact vulnerable versions.
How do I fix CVE-2023-37275?: Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround.
When was CVE-2023-37275 published?: CVE-2023-37275 was published on 2023-07-13 and last updated on 2026-06-17.

References

Affected products (1)

cpe:2.3:a:agpt:autogpt_classic:*:*:*:*:*:*:*:*

More vulnerabilities in Agpt Autogpt Classic

CVE-2024-8156 — Critical (CVSS 9.8): A command injection vulnerability exists in the workflow-checker.yml workflow of significant-gravitas/autogpt. The…
CVE-2024-6091 — Critical (CVSS 9.8): A vulnerability in significant-gravitas/autogpt version 0.5.1 allows an attacker to bypass the shell commands denylist…
CVE-2024-1881 — Critical (CVSS 9.8): AutoGPT, a component of significant-gravitas/autogpt, is vulnerable to an improper neutralization of special elements…
CVE-2024-1879 — High (CVSS 8.8): A Cross-Site Request Forgery (CSRF) vulnerability in significant-gravitas/autogpt version v0.5.0 allows attackers to…
CVE-2023-37273 — High (CVSS 8.1): Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. Running…
CVE-2024-1880 — High (CVSS 7.8): An OS command injection vulnerability exists in the MacOS Text-To-Speech class MacOSTTS of the…

All CVEs affecting Agpt Autogpt Classic →

Other CWE-117 (Improper Output Neutralization for Logs) vulnerabilities

CVE-2023-46322 — Critical (CVSS 9.8): iTermSessionLauncher.m in iTerm2 before 3.5.0beta12 does not sanitize ssh hostnames in URLs. The hostname's initial…
CVE-2023-46321 — Critical (CVSS 9.8): iTermSessionLauncher.m in iTerm2 before 3.5.0beta12 does not sanitize paths in x-man-page URLs. They may have shell…
CVE-2024-0095 — Critical (CVSS 9.0): NVIDIA Triton Inference Server for Linux and Windows contains a vulnerability where a user can inject forged logs and…
CVE-2024-25047 — High (CVSS 8.6): IBM Cognos Analytics 11.2.0 through 11.2.4 and 12.0.0 through 12.0.2 is vulnerable to injection attacks in application…
CVE-2025-57564 — High (CVSS 8.2): CubeAPM nightly-2025-08-01-1 allow unauthenticated attackers to inject arbitrary log entries into production systems…
CVE-2026-10745 — High (CVSS 7.9): Improper output neutralization for logs vulnerability in upKeeper Solutions upKeeper Instant Privilege Access on…

Browse all CWE-117 (Improper Output Neutralization for Logs) vulnerabilities →