# ModelTC LightLLM.

Every CVE that names ModelTC LightLLM among its affected products, newest first. Vendors and products are as the CNA wrote them.

## Records, newest first

- [LightLLM through 1.2.0 Unauthenticated DoS via pd_kv_trans_params Deserialization](https://agentprime.io/advisories/CVE-2026-111160.md)
  `CVE-2026-111160` · CVE record: ModelTC LightLLM · CVSS 8.7 High · Not analysed yet · Published 15 Oct 2026 · Tags: Insecure deserialization
- [LightLLM through 1.2.0 Unauthenticated Remote Code Execution via Visual-Only RPyC Service](https://agentprime.io/advisories/CVE-2026-103395.md)
  `CVE-2026-103395` · CVE record: ModelTC LightLLM · CVSS 9.3 Critical · Critical (CVSS 9+) · Not analysed yet · Published 30 Sept 2026 · Tags: Insecure deserialization
- [LightLLM through 1.2.0 Missing Authentication on RL Control Routes](https://agentprime.io/advisories/CVE-2026-103270.md)
  `CVE-2026-103270` · CVE record: ModelTC LightLLM · CVSS 8.7 High · Not analysed yet · Published 30 Sept 2026 · Tags: Authentication bypass
- [LightLLM through 1.2.0 Server-Side Request Forgery via multimodal endpoints](https://agentprime.io/advisories/CVE-2026-103243.md)
  `CVE-2026-103243` · CVE record: ModelTC LightLLM · CVSS 6.9 Medium · Not analysed yet · Published 30 Sept 2026 · Tags: Server-side request forgery (SSRF)
- [LightLLM through 1.2.0 Unauthenticated Memory Exhaustion via NCCL Control Channel set_value](https://agentprime.io/advisories/CVE-2026-103042.md)
  `CVE-2026-103042` · CVE record: ModelTC LightLLM · CVSS 8.7 High · Not analysed yet · Published 29 Sept 2026 · Tags: Denial of service
- [LightLLM through 1.2.0 Unauthenticated Remote Code Execution via Embed Cache RPyC Service](https://agentprime.io/advisories/CVE-2026-103041.md)
  `CVE-2026-103041` · CVE record: ModelTC LightLLM · CVSS 9.3 Critical · Critical (CVSS 9+) · Not analysed yet · Published 29 Sept 2026 · Tags: Insecure deserialization
- [LightLLM through 1.2.0 Unauthenticated Remote Code Execution via Router Profiler RPyC Service](https://agentprime.io/advisories/CVE-2026-103040.md)
  `CVE-2026-103040` · CVE record: ModelTC LightLLM · CVSS 9.3 Critical · Critical (CVSS 9+) · Not analysed yet · Published 29 Sept 2026 · Tags: Insecure deserialization
- [LightLLM through 1.2.0 Unauthenticated Remote Code Execution via NCCL PD RPyC Control Channel](https://agentprime.io/advisories/CVE-2026-96560.md)
  `CVE-2026-96560` · CVE record: ModelTC LightLLM · CVSS 9.3 Critical · Critical (CVSS 9+) · Not analysed yet · Published 23 Sept 2026 · Tags: Insecure deserialization
- [LightLLM through 1.2.0 Missing Authentication in PD Master /pd_register WebSocket Endpoint](https://agentprime.io/advisories/CVE-2026-93839.md)
  `CVE-2026-93839` · CVE record: ModelTC LightLLM · CVSS 9.3 Critical · Critical (CVSS 9+) · Not analysed yet · Published 18 Sept 2026 · Tags: Authentication bypass
- [LightLLM through 1.2.0 Unauthenticated Remote Code Execution via Config Server Pickle Deserialization](https://agentprime.io/advisories/CVE-2026-90919.md)
  `CVE-2026-90919` · CVE record: ModelTC LightLLM · CVSS 9.3 Critical · Critical (CVSS 9+) · Not analysed yet · Published 14 Sept 2026 · Tags: Insecure deserialization
- [LightLLM <= 1.1.0 PD Mode Unsafe Deserialization RCE](https://agentprime.io/advisories/CVE-2026-26220.md)
  `CVE-2026-26220` · CVE record: ModelTC LightLLM · CVSS 9.3 Critical · Critical (CVSS 9+) · Not analysed yet · Published 17 Feb 2026 · Tags: Insecure deserialization

## Filters and formats

Filters are query parameters on this URL: `q` (words, as in a web search engine: `"a phrase"`, `OR`, `-word`; an id; a package or product name), `severity` (low, medium, high or critical), `critical=1`, `kev=1`, `ecosystem` (npm, pypi, packagist, go, maven, rubygems, crates, nuget, hex), `kind=package`, `assigner` (a CNA’s short name), `min_score` and `state`. Each record’s title links to its Markdown page.

- The same list as JSON: <https://api.agentprime.io/v1/advisories?technology=modeltc-lightllm>
- Every list: <https://agentprime.io/advisories.md>, critical: <https://agentprime.io/advisories/critical.md>; by weakness: <https://agentprime.io/advisories/tag/sql-injection.md> and the other tags in <https://agentprime.io/llms.txt>; by technology: `/advisories/technology/<slug>.md` (`fortinet-fortimail`)

---

The web page: <https://agentprime.io/advisories/technology/modeltc-lightllm/>. Everything for agents: <https://agentprime.io/llms.txt>.