CVE-2026-111160: Deserialization of Untrusted Data in ModelTC LightLLM
Description
LightLLM versions up to 1.2.0 have a denial of service vulnerability in the /generate endpoint. An unauthenticated attacker can supply crafted data to the internal pd_kv_trans_params field, causing a failure in pickle.loads within InferSamplingParams. This crash kills the inference thread, causing subsequent requests to hang until the service is restarted, although the /health endpoint remains responsive.
CVSS v4.0
Score 8.7high
Affected software
ModelTC
LightLLM
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-111160 describes a denial of service vulnerability in ModelTC's LightLLM through version 1.2.0. The issue arises from deserialization of untrusted data via the internal pd_kv_trans_params field sent to the /generate endpoint. When pickle.loads fails during processing in InferSamplingParams, it crashes the inference worker thread. While the health endpoint remains up, all further inference requests hang indefinitely until a manual restart occurs.
Potential Impact
An unauthenticated attacker can cause a denial of service by crashing the inference worker thread, resulting in a hang of all subsequent inference requests. This disrupts service availability until the system is manually restarted. The health endpoint remains responsive, which may mask the underlying failure.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, consider restricting access to the /generate endpoint or implementing input validation to block malicious payloads targeting the pd_kv_trans_params field.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulnCheck
- Date Reserved
- 2026-10-15T17:04:03.418Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6ad123b82cdf04f65652b714
Added to database: 10/15/2026, 19:04:24 UTC
Last enriched: 10/15/2026, 19:33:24 UTC
Last updated: 10/15/2026, 19:33:24 UTC
Views: 7
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.