Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2023-37275— System logs spoofable in Auto-GPT via ANSI control sequences

Quick assessment

Affected
Significant-Gravitas Auto-GPT
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

Auto-GPT是Significant Gravitas开源的一个人工智能软件代理程序。 Auto-GPT 0.4.3之前版本存在安全漏洞，该漏洞源于恶意外部资源可能会通过让 LLM 反省 JSON 编码的 ANSI 转义序列 ( ) 来导致将误导性消息打印到控制台。

CVSS 3.1 · Low EPSS 0.44% · P36

Possible ATT&CK Techniques 1 AI

T1059 · Command and Scripting Interpreter
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2023-37275

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
System logs spoofable in Auto-GPT via ANSI control sequences
Source: CVE Program / CVE List V5
Vulnerability 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.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:L/A:N
Source: CVE Program / CVE List V5
Vulnerability Type
日志输出的转义处理不恰当
Source: CVE Program / CVE List V5
Vulnerability Title
Auto-GPT 安全漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
Auto-GPT是Significant Gravitas开源的一个人工智能软件代理程序。 Auto-GPT 0.4.3之前版本存在安全漏洞，该漏洞源于恶意外部资源可能会通过让 LLM 反省 JSON 编码的 ANSI 转义序列 ( ) 来导致将误导性消息打印到控制台。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

Vendor Product Affected Versions CPE Subscribe
Significant-Gravitas Auto-GPT < 0.4.3 -

II. Public POCs for CVE-2023-37275

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2023-37275

请登录查看更多情报信息。

Patches & Fixes for CVE-2023-37275 (1)

Vendor Advisories for CVE-2023-37275 (1)

Same Patch Batch · Significant-Gravitas · 2023-07-13 · 3 CVEs total

CVE-2023-37273 8.1 HIGH Docker escape in Auto-GPT when running from docker-compose.yml included in git repo
CVE-2023-37274 7.6 HIGH Python code execution sandbox escape in non-docker version in Auto-GPT

IV. Related Vulnerabilities

Same product: Auto-GPT
Same vendor: Significant-Gravitas
Same weakness: CWE-117

V. Comments for CVE-2023-37275

No comments yet

Leave a comment