CVE-2026-7304

published 2026-05-18 5 mo ago modified 2026-10-14 25 d ago also GHSA-36m8-w8qf-g76p , PYSEC-2026-535 , EUVD-2026-30766

cvss: 9.8; version 3.1, CNA
cisa kev: Not listed; not in CISA's catalog
epss: 0.6%; EPSS 0.6% chance of exploitation in 30 days, percentile 48%
public exploits: 0; none known

SGLangs multimodal generation runtime is vulnerable to unauthenticated remote code execution when the --enable-custom-logit-processor option is enabled, as Python objects loaded via dill.loads() will be deserialized without validation.

CISA SSVC

Exploitation: none
Automatable: yes
Technical impact: total
Assessed: 5 mo ago (2026-05-18)

Exploit prediction

0.58% chance of exploitation in the next 30 days, higher than 48% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by	version	score	vector
CISA ADP	3.1	9.8	CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CNA	3.1	9.8	CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
GitHub	3.1	9.8	CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
OSV	3.1	9.8	CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Affected packages

ecosystem	package	affected	fixed in
pypi	sglang	>=0.4.1.post7, <=0.5.12	no fix listed

Affected products

SGLang SGLang

Classification

Weakness

CWE-502 Deserialization of Untrusted Data

References

github.com /sgl-project/sglang/tree/main/python/sglang
web, product
antiproof.ai /blog/three-rces-in-sglang/
permissions-required
nvd.nist.gov /vuln/detail/CVE-2026-7304
advisory
antiproof.ai /blog/three-rces-in-sglang
web
github.com /sgl-project/sglang
package
pypi.org /project/sglang
package
github.com /advisories/GHSA-36m8-w8qf-g76p
advisory

Sources

Fencer Vulns 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.

Summary