Security Digest · Vulnerability record
CVE-2026-7304: SGLang: Unauthenticated RCE via --enable-custom-logit-processor
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.
CVSS 9.8 Critical EPSS 0.9% · p59
Should you act?
Critical and remotely reachable
No known exploitation yet, but it is network-reachable without credentials. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.
- No confirmed exploitation. It is not in CISA’s KEV catalog and CISA’s SSVC assessment records no known exploitation. That can change quickly after a public write-up; re-check if you are affected.
- EPSS 0.9%, percentile 59: FIRST’s model estimates a 0.9% chance of exploitation activity in the next 30 days, higher than 59% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
- Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
- Only applies if your dependency tree includes
sglang(PyPI) >= 0.4.1.post7, <= 0.5.12, no fixed version listed. Check your lockfile, including transitive dependencies.
What it is
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.
From the GitHub advisory
SGLang's 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.
Weakness type: CWE-502.
Product: sglang (PyPI) · Assigned by: certcc · Published: 2026-05-18
Affected and fixed versions
| Ecosystem | Package | Vulnerable | First fixed |
|---|---|---|---|
| PyPI | sglang | >= 0.4.1.post7, <= 0.5.12 | none listed |
| Vendor | Product | Affected versions (per CVE record) |
|---|---|---|
| SGLang | SGLang | 5.10 |
Severity scores
| Scored by | CVSS | Score | Vector |
|---|---|---|---|
| CISA-ADP | 3.1 | 9.8 Critical | 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 |
- Attack vector: network (remotely reachable)
- Attack complexity: low
- Privileges required: none (no login)
- User interaction: none
- Scope: unchanged
CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.
Exploitation and urgency
- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation none, automatable yes, technical impact total.
- FIRST EPSS (model of 2026-10-21): 0.88% probability of exploitation activity in the next 30 days; percentile 59.
Timeline
- — CVE record last updated
- — CVE record published by certcc
- — GitHub-reviewed advisory GHSA-36m8-w8qf-g76p published (critical)
Sources and references
Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.
Vulnerability records
- GitHub Advisory GHSA-36m8-w8qf-g76p github.com
- CVE.org record CVE-2026-7304 cve.org
- NVD entry CVE-2026-7304 nvd.nist.gov
Other references from the CVE record and advisory
- github.com github.com
- antiproof.ai antiproof.ai