CVE-2026-63764
LMDeploy Server-Side Request Forgery via HTTP Redirect Bypass
Description
LMDeploy through 0.14.0, fixed in commit 03c3130, contains a server-side request forgery (SSRF) vulnerability in the _load_http_url function within the connection.py media handler, where the private-IP guard validates only the original URL without re-validating hosts after HTTP redirects. An unauthenticated attacker can submit a crafted image_url to the chat completions endpoint pointing to an attacker-controlled host that returns a redirect to a private IP or cloud-metadata endpoint, causing the server to follow the redirect and expose internal service content through the model pipeline.
INFO
Published Date :
July 21, 2026, 9:16 p.m.
Last Modified :
Aug. 5, 2026, 7:44 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS | 134c704f-9b21-4f2e-91b3-4a467353bcc0 | |||||
| CVSS 3.1 | CRITICAL | 83251b91-4cc7-4094-a5c7-464a1b83ea10 | ||||
| CVSS 3.1 | CRITICAL | [email protected] | ||||
| CVSS 3.1 | HIGH | [email protected] | ||||
| CVSS 4.0 | CRITICAL | 83251b91-4cc7-4094-a5c7-464a1b83ea10 | ||||
| CVSS 4.0 | CRITICAL | [email protected] | ||||
| CVSS 4.0 | HIGH | [email protected] |
Solution
- Update lmdeploy to the latest version.
- Configure stricter URL validation for image_url.
- Implement checks for redirecting URLs.
- Monitor network traffic for suspicious requests.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-63764.
| URL | Resource |
|---|---|
| https://github.com/InternLM/lmdeploy/commit/03c313006d17cc3feae86b633c44206a997c44db | Patch |
| https://github.com/InternLM/lmdeploy/issues/4761 | Exploit Issue Tracking Mitigation |
| https://github.com/InternLM/lmdeploy/pull/4734 | Issue Tracking Patch |
| https://www.vulncheck.com/advisories/lmdeploy-server-side-request-forgery-via-http-redirect-bypass | Exploit Patch Third Party Advisory |
| https://github.com/InternLM/lmdeploy/issues/4761 | Exploit Issue Tracking Mitigation |
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-63764 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-63764
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-63764 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-63764 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
Initial Analysis by [email protected]
Aug. 05, 2026
Action Type Old Value New Value Added CPE Configuration OR *cpe:2.3:a:internlm:lmdeploy:*:*:*:*:*:*:*:* versions up to (including) 0.14.0 Added Reference Type VulnCheck: https://github.com/InternLM/lmdeploy/commit/03c313006d17cc3feae86b633c44206a997c44db Types: Patch Added Reference Type VulnCheck: https://github.com/InternLM/lmdeploy/issues/4761 Types: Exploit, Issue Tracking, Mitigation Added Reference Type VulnCheck: https://github.com/InternLM/lmdeploy/pull/4734 Types: Issue Tracking, Patch Added Reference Type VulnCheck: https://www.vulncheck.com/advisories/lmdeploy-server-side-request-forgery-via-http-redirect-bypass Types: Exploit, Patch, Third Party Advisory Added Reference Type CISA-ADP: https://github.com/InternLM/lmdeploy/issues/4761 Types: Exploit, Issue Tracking, Mitigation -
CVE Modified by [email protected]
Jul. 23, 2026
Action Type Old Value New Value Changed Affected [{'vendor': 'InternLM', 'product': 'lmdeploy', 'versions': [{'status': 'unknown', 'version': '648df3b', 'versionType': 'git'}], 'defaultStatus': 'affected'}] [{'repo': 'https://github.com/InternLM/lmdeploy', 'vendor': 'InternLM', 'product': 'lmdeploy', 'versions': [{'status': 'affected', 'version': '0', 'versionType': 'semver', 'lessThanOrEqual': '0.14.0'}, {'status': 'unaffected', 'version': '03c313006d17cc3feae86b633c44206a997c44db', 'versionType': 'git'}], 'packageURL': 'pkg:pypi/requirements.txt', 'defaultStatus': 'unaffected'}] Changed Description lmdeploy's OpenAI-compatible API server contains a server-side request forgery vulnerability that allows unauthenticated attackers to access internal services and cloud metadata endpoints by supplying a crafted image_url that redirects to internal targets. Attackers can send a POST request to the chat completions endpoint with an image_url pointing to an attacker-controlled server that responds with an HTTP 302 redirect to internal addresses such as loopback or instance-metadata endpoints, bypassing the initial URL safety check because redirects are followed without re-validating each hop through the safety guard. LMDeploy through 0.14.0, fixed in commit 03c3130, contains a server-side request forgery (SSRF) vulnerability in the _load_http_url function within the connection.py media handler, where the private-IP guard validates only the original URL without re-validating hosts after HTTP redirects. An unauthenticated attacker can submit a crafted image_url to the chat completions endpoint pointing to an attacker-controlled host that returns a redirect to a private IP or cloud-metadata endpoint, causing the server to follow the redirect and expose internal service content through the model pipeline. Added CVSS V4.0 AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:N/SC:H/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X Removed CVSS V4.0 AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:H/VA:L/SC:N/SI:H/SA:L/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X Added CVSS V3.1 AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N Removed CVSS V3.1 AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N Added Reference https://github.com/InternLM/lmdeploy/commit/03c313006d17cc3feae86b633c44206a997c44db Added Reference https://github.com/InternLM/lmdeploy/pull/4734 Added Reference https://www.vulncheck.com/advisories/lmdeploy-server-side-request-forgery-via-http-redirect-bypass Removed Reference https://github.com/InternLM/lmdeploy Removed Reference https://www.vulncheck.com/advisories/lmdeploy-server-side-request-forgery-via-http-redirect-bypass-of-private-ip-guard-in-vision-image-fetch -
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
Jul. 23, 2026
Action Type Old Value New Value Added Reference https://github.com/InternLM/lmdeploy/issues/4761 Added SSVC {'id': 'CVE-2026-63764', 'role': 'CISA Coordinator', 'options': [{'exploitation': 'poc'}, {'automatable': 'yes'}, {'technicalImpact': 'partial'}], 'version': '2.0.3', 'timestamp': '2026-07-23T14:12:09.324972Z'} -
New CVE Received by [email protected]
Jul. 21, 2026
Action Type Old Value New Value Added Affected [{'vendor': 'InternLM', 'product': 'lmdeploy', 'versions': [{'status': 'unknown', 'version': '648df3b', 'versionType': 'git'}], 'defaultStatus': 'affected'}] Added Description lmdeploy's OpenAI-compatible API server contains a server-side request forgery vulnerability that allows unauthenticated attackers to access internal services and cloud metadata endpoints by supplying a crafted image_url that redirects to internal targets. Attackers can send a POST request to the chat completions endpoint with an image_url pointing to an attacker-controlled server that responds with an HTTP 302 redirect to internal addresses such as loopback or instance-metadata endpoints, bypassing the initial URL safety check because redirects are followed without re-validating each hop through the safety guard. Added CVSS V4.0 AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:H/VA:L/SC:N/SI:H/SA:L/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X Added CVSS V3.1 AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N Added CWE CWE-918 Added Reference https://github.com/InternLM/lmdeploy Added Reference https://github.com/InternLM/lmdeploy/issues/4761 Added Reference https://www.vulncheck.com/advisories/lmdeploy-server-side-request-forgery-via-http-redirect-bypass-of-private-ip-guard-in-vision-image-fetch