Vulnerability in Agpt Autogpt Classic
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.
EPSS: 0.004 (35.8th percentile) — read the EPSS interpretation.
CVSS v3 metric
CVSS v3 base score 3.1 (Low). Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:L/A:N.
Affected products
- Agpt Autogpt_classic
- Significant-gravitas Auto-gpt — versions < 0.4.3
Weakness classification (CWE)
Public proof-of-concept exploits
References
- security-advisories@github.com (x_refsource_CONFIRM, Patch, Third Party Advisory)
- security-advisories@github.com (Patch, Third Party Advisory, x_refsource_MISC)
Frequently asked questions
- What is CVE-2023-37275?
- CVE-2023-37275 is a low-severity vulnerability in Agpt Autogpt Classic, classified under Improper Output Neutralization for Logs. CVSS score: 3.1/10. Published 2023-07-13.
- How severe is CVE-2023-37275?
- Low severity. CVSS v3 base score is 3.1 out of 10.
- Is CVE-2023-37275 known to be exploited?
- 1 public proof-of-concept repositories are indexed. Not currently listed in the CISA KEV catalog.