PatchSiren cyber security CVE debrief
CVE-2026-105245 sgl-project CVE debrief
A vulnerability was found in sgl-project sglang up to 0.5.21, affecting the server_info function in python/sglang/srt/entrypoints/http_server.py. This issue allows for cleartext transmission of sensitive information via manipulation of the api_key argument in the HTTP Endpoint. The attack can be launched remotely and is considered difficult to exploit. The exploit has been disclosed publicly and a pull request for a fix is pending acceptance.
- Vendor
- sgl-project
- Product
- sglang
- CVSS
- LOW 2.9
- CISA KEV
- Not listed in stored evidence
- Original CVE published
- 2026-10-05
- Original CVE updated
- 2026-10-05
- Advisory published
- 2026-10-05
- Advisory updated
- 2026-10-05
Who should care
Defenders responsible for configuring and securing HTTP endpoints should assess exposure to this vulnerability. This includes reviewing the configuration of the affected component and ensuring that sensitive data is transmitted securely.
Why it matters
CVE-2026-105245 allows cleartext transmission of sensitive information in sglang. Defenders should verify secure communication protocols, review HTTP endpoint configurations, and monitor for exploitation attempts.
- Verification of secure communication protocols is required to prevent cleartext transmission of sensitive information.
- Defenders must review HTTP endpoint configurations to ensure secure data transmission.
- Exploitation attempts targeting this vulnerability should be monitored and addressed promptly.
Technical summary
The vulnerability affects the server_info function in python/sglang/srt/entrypoints/http_server.py, allowing for cleartext transmission of sensitive information via manipulation of the api_key argument. The attack can be launched remotely and is considered difficult to exploit. This issue arises from inadequate secure communication protocols, potentially exposing sensitive information. Defenders should assess the configuration of affected HTTP endpoints and prioritize verifying secure communication protocols to protect sensitive information in transit.
Defensive priority
Defenders should prioritize verifying the use of secure communication protocols to protect sensitive information in transit. This involves reviewing the configuration of the HTTP endpoint and ensuring that sensitive data, such as API keys, is transmitted securely.
Recommended defensive actions
- Verify the use of secure communication protocols to protect sensitive information in transit
- Review the configuration of the HTTP endpoint to prevent cleartext transmission of sensitive data
- Monitor for potential exploitation attempts targeting this vulnerability
- Review compensating controls for exposed systems while remediation is scheduled and verified
- Check relevant monitoring, detection, and logs for exposed assets that need extra review
- Track exceptions, retest remediated assets, and close the item only after evidence is documented
- Confirm whether affected product deployments exist in managed environments and assign an owner for follow-up
Evidence notes
The CVE record and NVD detail page provide information on the vulnerability, including its description, CVSS score, and affected versions. However, the corpus does not establish specific versions that are vulnerable or fixed, or confirm exploitation.
Sources and references
Verified primary and authoritative sources
-
CVE-2026-105245 CVE Program record
Publisher, destination, and source semantics verified
URL: https://www.cve.org/CVERecord?id=CVE-2026-105245
CVE Program - Official CVE Program record with source-provided CVE metadata.
-
CVE-2026-105245 NVD vulnerability detail
Publisher, destination, and source semantics verified
URL: https://nvd.nist.gov/vuln/detail/CVE-2026-105245
NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.
Supplemental references
-
Source reference
Unverified legacy reference
URL: https://github.com/sgl-project/sglang/
-
Source reference
Unverified legacy reference
URL: https://github.com/sgl-project/sglang/issues/30166
-
Source reference
Unverified legacy reference
URL: https://github.com/sgl-project/sglang/pull/30343
-
Source reference
Unverified legacy reference
URL: https://vuldb.com/cve/CVE-2026-105245
-
Source reference
Unverified legacy reference
URL: https://vuldb.com/submit/975910
-
Source reference
Unverified legacy reference
URL: https://vuldb.com/vuln/413451
-
Source reference
Unverified legacy reference
URL: https://vuldb.com/vuln/413451/cti
Methodology and review provenance
AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.