PatchSiren cyber security CVE debrief
CVE-2026-90919 ModelTC CVE debrief
CVE-2026-90919 is a critical remote code execution vulnerability in LightLLM's Config Server. The vulnerability exists in the unauthenticated /visual_register WebSocket endpoint, which passes client frames directly to pickle.loads(). This allows attackers to execute arbitrary code with Config Server process privileges by sending a malicious serialized payload with a __reduce__ method.
- Vendor
- ModelTC
- Product
- LightLLM
- CVSS
- CRITICAL 9.3
- CISA KEV
- Not listed in stored evidence
- Original CVE published
- 2026-09-14
- Original CVE updated
- 2026-09-23
- Advisory published
- 2026-09-14
- Advisory updated
- 2026-09-23
Who should care
Defenders responsible for LightLLM deployments, security teams, and vulnerability management teams should assess exposure and apply remediation to prevent exploitation. This includes reviewing the Config Server's accessibility, updating to a fixed version of LightLLM, and monitoring for suspicious activity. Operators and administrators of affected systems must prioritize verifying exposure and applying necessary patches or mitigations.
Why it matters
CVE-2026-90919 is a critical remote code execution vulnerability in LightLLM's Config Server. Defenders should prioritize verifying exposure and applying remediation to prevent exploitation.
- Verify exposure to prevent potential code execution
- Apply remediation to prevent exploitation
- Monitor for suspicious activity on the Config Server
- Implement compensating controls to restrict access to the Config Server
Technical summary
The vulnerability exists in the unauthenticated /visual_register WebSocket endpoint of LightLLM's Config Server. The endpoint passes the first client frame directly to pickle.loads(), allowing attackers to execute arbitrary code with Config Server process privileges by sending a malicious serialized payload with a __reduce__ method. This critical remote code execution vulnerability affects LightLLM version 1.2.0 and allows for arbitrary code execution with Config Server privileges, impacting defenders who need to verify exposure and apply remediation.
Defensive priority
Defenders should prioritize verifying exposure and applying remediation to prevent exploitation.
Recommended defensive actions
- Verify exposure by checking if the Config Server is running and accessible
- Apply remediation by updating LightLLM to a version that fixes the vulnerability
- Monitor for suspicious activity on the Config Server
- Implement compensating controls to restrict access to the Config Server
- Review 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 entry provide details on the vulnerability, including its critical CVSS score of 9.3 and the affected LightLLM version 1.2.0. Evidence is limited to public CVE and NVD data. Defenders should verify exposure with available information and review vendor advisories for specific guidance on affected configurations and remediation steps.
Sources and references
Verified primary and authoritative sources
-
CVE-2026-90919 CVE Program record
Publisher, destination, and source semantics verified
URL: https://www.cve.org/CVERecord?id=CVE-2026-90919
CVE Program - Official CVE Program record with source-provided CVE metadata.
-
CVE-2026-90919 NVD vulnerability detail
Publisher, destination, and source semantics verified
URL: https://nvd.nist.gov/vuln/detail/CVE-2026-90919
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/ModelTC/LightLLM/blob/v1.2.0/lightllm/server/config_server/api_http.py
-
Source reference
Unverified legacy reference
URL: https://github.com/ModelTC/LightLLM/issues/1563
-
Source reference
Unverified legacy reference
URL: https://github.com/ModelTC/lightllm
-
Source reference
Unverified legacy reference
URL: https://www.vulncheck.com/advisories/lightllm-through-1.2.0-unauthenticated-remote-code-execution-via-config-server-pickle-deserialization
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.