MediumVulnerabilityLLM-specific

CVE-2026-6607: lm-sys FastChat resource consumption in Worker API Endpoint api_generate

Source: NVD(opens in a new tab)
Identifier: CVE-2026-6607
Published: April 20, 2026
Record updated: October 9, 2026

Affected: fschat <= 0.2.26
Fixed in: No fixed version was stated when the source was last read.
Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.7%

Summary

CVE-2026-6607 affects lm-sys FastChat up to 0.2.36. A manipulation of the api_generate function in the Worker API Endpoint component leads to resource consumption and can be initiated remotely, and a public exploit has been disclosed.

Mitigation

Install the patch identified as c9e84b89c91d45191dc24466888de526fa04cf33. Commit ff66426 patched api_generate in base_model_worker.py but did not cover other entry points.

Details

Scores and exploitation

CVSS score: 5.3(medium)
CVSS vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L
Attack vector: network
Attack complexity: low
Privileges required: none
User interaction: none
EPSS: 0.7%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on October 13, 2026.
Disclosure date: April 20, 2026

Weaknesses and techniques

Weakness (CWE): CWE-400
CWE-404
Attack pattern (CAPEC): CAPEC-125
CAPEC-130

Affected

Packages: fschat@<= 0.2.26

Classification

Attack type: Denial of service
Attack sophistication: Trivial
AI component targeted: Inference
Impact: Availability
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-6607

First tracked: April 20, 2026 at 08:18 AM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 90% (self-assessed)

Affected packages in the Exposure Registry

Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.

fschatPyPILLM dependency since 2023-04-16

Summary

Mitigation

Affected packages in the Exposure Registry

Related items