Vendor
ModelTC
12 known vulnerabilities.
ModelTC at a glance
- Last 12 months
- 12
- Critical · all time
- 7
- Exploited · all time
- 0
- Public exploit · all time
- 0
Show as table
| Month | Vulnerabilities | Critical |
|---|---|---|
| Nov 2026 | 0 | 0 |
| Oct 2026 | 2 | 0 |
| Sep 2026 | 9 | 6 |
| Aug 2026 | 0 | 0 |
| Jul 2026 | 0 | 0 |
| Jun 2026 | 0 | 0 |
| May 2026 | 0 | 0 |
| Apr 2026 | 0 | 0 |
| Mar 2026 | 0 | 0 |
| Feb 2026 | 1 | 1 |
| Jan 2026 | 0 | 0 |
| Dec 2025 | 0 | 0 |
| Nov 2025 | 0 | 0 |
| Oct 2025 | 0 | 0 |
| Sep 2025 | 0 | 0 |
| Aug 2025 | 0 | 0 |
| Jul 2025 | 0 | 0 |
| Jun 2025 | 0 | 0 |
| May 2025 | 0 | 0 |
| Apr 2025 | 0 | 0 |
| Mar 2025 | 0 | 0 |
| Feb 2025 | 0 | 0 |
| Jan 2025 | 0 | 0 |
| Dec 2024 | 0 | 0 |
Products
12 results · Feed
-
High 7.5
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 pd_kv_trans_params field to the /generate endpoint. Attackers can send a single request whose param…
-
Medium 5.3
ModelTC LightX2V Tokenizer cosmos3_runner.py AutoTokenizer.from_pretrained code injection
A weakness has been identified in ModelTC LightX2V up to 0.5.0. Affected is the function AutoTokenizer.from_pretrained of the file lightx2v/models/runners/cosmos3/cosmos3_runner.py of the component Tokenizer. This manipulation of the argument auto_map causes …
-
High 7.5
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 /pause_generation, /abort_request, /flush_cache, and /init_weights_update_group to disr…
-
Critical 9.8
LightLLM through 1.2.0 Unauthenticated Remote Code Execution via Visual-Only RPyC Service
LightLLM through 1.2.0 visual_only deployments expose an unauthenticated RPyC service with allow_pickle enabled that deserializes attacker-supplied arguments in the remote_infer_images method. Attackers can reach the visual RPyC port and pass objects with __r…
-
Medium 5.8
LightLLM through 1.2.0 Server-Side Request Forgery via multimodal endpoints
LightLLM through 1.2.0 fails to validate image_url and audio_url 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 …
-
High 7.5
LightLLM through 1.2.0 Unauthenticated Memory Exhaustion via NCCL Control Channel set_value
LightLLM through 1.2.0 contains a memory exhaustion vulnerability in the NCCL control channel when started with --pd_trans_mode nccl, allowing unauthenticated attackers to exhaust KV-transfer worker memory. Attackers can call the exposed_set_value method to s…
-
Critical 9.8
LightLLM through 1.2.0 Unauthenticated Remote Code Execution via Router Profiler RPyC Service
LightLLM through 1.2.0 contains a remote code execution vulnerability in the router profiler service when started with --enable_profiling flag. The service exposes an unauthenticated RPyC server with pickle deserialization enabled, allowing attackers to execu…
-
Critical 9.8
LightLLM through 1.2.0 Unauthenticated Remote Code Execution via Embed Cache RPyC Service
LightLLM through 1.2.0 multimodal deployments expose an unauthenticated RPyC cache service with pickle deserialization enabled on all interfaces. Attackers can send crafted serialized objects to exposed cache methods to execute arbitrary code with service pri…
-
Critical 9.8
LightLLM through 1.2.0 Unauthenticated Remote Code Execution via NCCL PD RPyC Control Channel
LightLLM through 1.2.0 contains a remote code execution vulnerability in the KV-transfer worker when started with --pd_trans_mode nccl, which exposes an unauthenticated RPyC control channel that deserializes attacker-supplied data. Attackers can send maliciou…
-
Critical 9.8
LightLLM through 1.2.0 Missing Authentication in PD Master /pd_register WebSocket Endpoint
LightLLM through 1.2.0 contains an authentication bypass vulnerability in the /pd_register WebSocket endpoint that allows unauthenticated attackers to register arbitrary nodes by supplying crafted JSON without peer address validation. Attackers can disclose f…
-
Critical 9.8
LightLLM through 1.2.0 Unauthenticated Remote Code Execution via Config Server Pickle Deserialization
LightLLM through 1.2.0 contains a remote code execution vulnerability in the Config Server's unauthenticated /visual_register WebSocket endpoint that passes the first client frame directly to pickle.loads(). Attackers can reach the Config Server port and send…
-
Critical 9.3
LightLLM <= 1.1.0 PD Mode Unsafe Deserialization RCE
LightLLM version 1.1.0 and prior contain an unauthenticated remote code execution vulnerability in PD (prefill-decode) disaggregation mode. The PD master node exposes WebSocket endpoints that receive binary frames and pass the data directly to pickle.loads() …