CVE-2026-111160

LightLLM through 1.2.0 contains a denial of service vulnerability that allows unauthenticated attackers to crash the inference worker by supplying the internal pdkvtransparams field to the /generate endpoint. Attackers can send a single request whose parameters cause pickle.loads to fail in...

CVE-2026-111160

Versions of LightLLM through 1.2.0 are vulnerable to a denial of service (DoS) condition. An unauthenticated attacker can crash the inference worker by sending a single request to the /generate endpoint containing the internal pd_kv_trans_params field. The vulnerability stems from the use of pick...

EUVD-2026-102287

LightLLM through 1.2.0 contains a denial of service vulnerability that allows unauthenticated attackers to crash the inference worker by supplying the internal pdkvtransparams field to the /generate endpoint. Attackers can send a single request whose parameters cause pickle.loads to fail in...

CVE-2026-111160 LightLLM through 1.2.0 Unauthenticated DoS via pd_kv_trans_params Deserialization

LightLLM through 1.2.0 contains a denial of service vulnerability that allows unauthenticated attackers to crash the inference worker by supplying the internal pdkvtransparams field to the /generate endpoint. Attackers can send a single request whose parameters cause pickle.loads to fail in...

CVE-2026-111160 LightLLM through 1.2.0 Unauthenticated DoS via pd_kv_trans_params Deserialization

LightLLM through 1.2.0 contains a denial of service vulnerability that allows unauthenticated attackers to crash the inference worker by supplying the internal pdkvtransparams field to the /generate endpoint. Attackers can send a single request whose parameters cause pickle.loads to fail in...

CVE-2026-111160 LightLLM through 1.2.0 Unauthenticated DoS via pd_kv_trans_params Deserialization

LightLLM through 1.2.0 contains a denial of service vulnerability that allows unauthenticated attackers to crash the inference worker by supplying the internal pdkvtransparams field to the /generate endpoint. Attackers can send a single request whose parameters cause pickle.loads to fail in...

CVE-2026-111160

LightLLM through 1.2.0 contains a denial of service vulnerability that allows unauthenticated attackers to crash the inference worker by supplying the internal pdkvtransparams field to the /generate endpoint. Attackers can send a single request whose parameters cause pickle.loads to fail in...

CVE-2026-111160: Deserialization of Untrusted Data

LightLLM through 1.2.0 contains a denial of service vulnerability that allows unauthenticated attackers to crash the inference worker by supplying the internal pdkvtransparams field to the /generate endpoint. Attackers can send a single request whose parameters cause pickle.loads to fail in...

PT-2026-115166

Name of the Vulnerable Software and Affected Versions LightLLM versions prior to 1.2.1 Description An unauthenticated attacker can cause a denial of service by sending a request to the '/generate' endpoint containing the pd kv trans params field. This triggers a failure in the pickle.loads functi...

ModelTC LightLLM deserialization injection vulnerability

ModelTC LightLLM 1.2.0 and earlier versions have a deserialization injection vulnerability. This vulnerability arises when unverified attackers provide the internal pdkvtransparams field to the /generate endpoint, causing pickle.loads to fail in InferSamplingParams. This can lead to the collapse ...

CVE-2026-103395

LightLLM through 1.2.0 visualonly deployments expose an unauthenticated RPyC service with allowpickle enabled that deserializes attacker-supplied arguments in the remoteinferimages method. Attackers can reach the visual RPyC port and pass objects with reduce methods to execute arbitrary code with...

CVE-2026-103270

LightLLM through 1.2.0 mounts reinforcement learning control routes on the public HTTP API without authentication checks. Unauthenticated attackers can call endpoints like /pausegeneration, /abortrequest, /flushcache, and /initweightsupdategroup to disrupt inference operations and wedge workers o...

CVE-2026-103243

LightLLM through 1.2.0 fails to validate imageurl and audiourl parameters in multimodal endpoints, allowing unauthenticated attackers to perform server-side request forgery. Attackers can supply arbitrary URLs to fetch internal resources, with vision model processing disclosing content or error...

EUVD-2026-89989

LightLLM through 1.2.0 mounts reinforcement learning control routes on the public HTTP API without authentication checks. Unauthenticated attackers can call endpoints like /pausegeneration, /abortrequest, /flushcache, and /initweightsupdategroup to disrupt inference operations and wedge workers o...

CVE-2026-103395 LightLLM through 1.2.0 Unauthenticated Remote Code Execution via Visual-Only RPyC Service

LightLLM through 1.2.0 visualonly deployments expose an unauthenticated RPyC service with allowpickle enabled that deserializes attacker-supplied arguments in the remoteinferimages method. Attackers can reach the visual RPyC port and pass objects with reduce methods to execute arbitrary code with...

CVE-2026-103395 LightLLM through 1.2.0 Unauthenticated Remote Code Execution via Visual-Only RPyC Service

LightLLM through 1.2.0 visualonly deployments expose an unauthenticated RPyC service with allowpickle enabled that deserializes attacker-supplied arguments in the remoteinferimages method. Attackers can reach the visual RPyC port and pass objects with reduce methods to execute arbitrary code with...

CVE-2026-103270

LightLLM versions up to and including 1.2.0 are vulnerable to a missing authentication flaw on reinforcement learning (RL) control routes. When deployments are started with the --enable_rl flag, the software mounts specific control routes on the public HTTP API without requiring authentication ch...

CVE-2026-103270 LightLLM through 1.2.0 Missing Authentication on RL Control Routes

LightLLM through 1.2.0 mounts reinforcement learning control routes on the public HTTP API without authentication checks. Unauthenticated attackers can call endpoints like /pausegeneration, /abortrequest, /flushcache, and /initweightsupdategroup to disrupt inference operations and wedge workers o...

EUVD-2026-89990

LightLLM through 1.2.0 visualonly deployments expose an unauthenticated RPyC service with allowpickle enabled that deserializes attacker-supplied arguments in the remoteinferimages method. Attackers can reach the visual RPyC port and pass objects with reduce methods to execute arbitrary code with...

CVE-2026-103395

Versions of LightLLM through 1.2.0 with visual_only deployments are vulnerable to Unauthenticated Remote Code Execution (RCE) . The issue stems from an exposed RPyC service where the allow_pickle option is enabled, allowing the remote_infer_images method to deserialize untrusted arguments. An att...