SGLang: Deserialization of Untrusted Data
CVE-2026-93088 is a critical-severity deserialization of untrusted data vulnerability in SGLang, with a CVSS 3.1 base score of 9.8 out of 10. It can be exploited remotely over the network by an unauthenticated attacker, without any action from a user. Affected SGLang versions: 0.5.11 through 0.5.14. The record does not name a fixed version, so check the vendor advisory. There is no confirmed exploitation so far. EPSS estimates a 0.73% chance of exploitation within 30 days, higher than 55% of scored CVEs.
Critical severity: a successful attack would have severe impact.
What to do
- Check which version of SGLang you run against the affected versions below, and install the vendor's latest release.
- Until you can update, restrict network access to the affected service so it is not reachable from untrusted networks.
Affected products and versions
Version data comes from the organisation that assigned the CVE. Confirm against the vendor advisory before deciding you are unaffected.
How the severity score breaks down
- Attack vector
- NetworkCan be exploited remotely over a network, including the internet.
- Attack complexity
- LowNo special conditions are needed; the attack works reliably.
- Privileges required
- NoneNo account or login is needed.
- User interaction
- NoneNo action by a victim is required.
- Scope
- UnchangedImpact stays within the vulnerable component.
- Confidentiality
- HighAll data handled by the component can be read.
- Integrity
- HighData or code can be modified at will.
- Availability
- HighThe component can be taken down completely.
Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H. Scored by CISA (ADP).
Official description
SGLang's multimodal generation runtime is vulnerable to unauthenticated arbitrary code execution because the disaggregated-diffusion orchestrator's DiffusionServer binds an unauthenticated ZeroMQ ROUTER socket to a network interface and passes the final frame of received multipart messages directly to pickle.loads() before any validation occurs.
Source: the CVE record as published by its numbering authority, via NVD and CVE.org.
The underlying weakness: Deserialization of Untrusted Data
The product deserializes untrusted data without sufficiently ensuring that the resulting data will be valid.
How developers prevent this class of flaw
- If available, use the signing/sealing features of the programming language to assure that deserialized data has not been tainted. For example, a hash-based message authentication code (HMAC) could be used to ensure that data has not been modified.
- When deserializing data, populate a new object rather than just deserializing. The result is that the data flows through safe input validation and that the functions are safe.
- Explicitly define a final object() to prevent deserialization.
More Deserialization of Untrusted Data vulnerabilities (CWE-502)
Timeline
- CVE record published.
- CISA published its SSVC assessment (exploitation: poc, automatable: yes, technical impact: total).
References
Other references
Other vulnerabilities in SGLang
- 9.8 Critical severity
- 9.8 Critical severity
- 7.5 High severity
- 7.5 High severity
- 9.8 Critical severity
- 9.8 Critical severity
Recent Deserialization of Untrusted Data vulnerabilities
- 9.8 Critical severity
- 8.8 High severity
- 8.8 High severity
- 8.1 High severity
- 7.7 High severity
- 8.8 High severity
Spotted an error? Tell us.