Skip to content
Fencer Intel
high 7.5

CVE-2026-123818 json

LMDeploy URL parser disagreement permits SSRF filter bypass

published last mo. modified 2d ago also GHSA-39wr-7q6h-cf68 , EUVD-2026-120455

cvss
7.5
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.3%
EPSS 0.3% chance of exploitation in 30 days, percentile 21%
public exploits
0
none known

Summary

LMDeploy is a toolkit for compressing, deploying, and serving large language models. From 0.12.3 until 0.15.0, _is_safe_url validates remote media URLs with urlparse while requests.Session().get interprets backslashes differently when sending the request. An attacker can provide a URL whose validation hostname appears globally routable but whose request destination resolves to an internal host, bypassing non-global address checks. Applications that accept attacker-controlled remote media URLs can therefore be induced to access internal HTTP services and expose data available from those services. This issue is fixed in version 0.15.0.

Patch / fix

  • pypi lmdeploy 0.15.0

Is CVE-2026-123818 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

Exploit prediction

0.29% chance of exploitation in the next 30 days, higher than 21% of all scored CVEs (FIRST EPSS, 2026-11-11).

CVSS scores

assigned by version score vector
CNA 3.1 7.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
GitHub 3.1 7.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

Affected packages

ecosystem package affected fixed in
pypi lmdeploy
>=0.12.3, <0.15.0
0.15.0

Affected products

  • InternLM lmdeploy

Classification

Weakness

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.