CVE-2026-6607

MEDIUMNVD 5.35.3
EchelonGraph scoreMEDIUM confidence

“—” beside the score: it is equal to NVD's CVSS score.

Score 5.3 from GitHub Security Advisory published 2026-04-20. NVD baseline CVSS 5.3; sources differ by 0.0.

Triggered by: GitHub Security Advisory CVSS
Sources: EPSS, GitHub Security Advisory, NVD CVSS v3
Trending — 3 sources updated this weekElevated
5.3EG
EchelonGraph verdictPlan mitigationRemediate within your standard update timelines at low or medium mission impact and sooner than that at high (the SSVC decision on this page).
  • CISA's Vulnrichment rates exploitation as PoC; EchelonGraph holds no exploit-code reference for it
CISA-KEV: Not listedEPSS PROB: 0.7%CVSS: 5.3Exploit: No code on recordExposed services: Not assessed

An upstream fix is merged but not yet released — mitigate (WAF / firewall / segmentation) until the release ships, then apply it.

A security vulnerability has been detected in lm-sys fastchat up to 0.2.36. This issue affects the function api_generate of the component Worker API Endpoint. The manipulation leads to resource consumption. The attack can be initiated remotely. The exploit has been disclosed publicly and may be used. The identifier of the patch is c9e84b89c91d45191dc24466888de526fa04cf33. It is suggested to install a patch to address this issue. Commit ff66426 patched this issue in api_generate of base_model_worker.py and did miss other entry points.

CVSS v3
5.3
EG Score
5.3MEDIUMmedium confidence
EG Risk
55
EG Risk 55/100

EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).

How it’s computed (value × EchelonGraph’s weight)
Severity53% × 45%
The EG Score, 5.3 of 10.
Exploitation40% × 40%
EchelonGraph's fixed weight for EG-KEV Tier 3 (Elevated): a constant, not a probability.
Automatability100% × 15%
CISA's SSVC Automatable value: yes (Vulnrichment).
SSVC (CISA's decision table, applied by EchelonGraph): Track at low or medium mission impact; Attend at high (mission-essential systems).
Exploitation public PoC (CISA Vulnrichment) · Automatable yes (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE.
Action: An upstream fix is merged but not yet in a tagged release. Restrict network exposure of the affected system or apply the vendor's mitigation within your standard update timelines at low or medium mission impact and sooner than that at high until it ships, then apply the release.
EPSS PROB
0.7%
EPSS %ILE
53rd
KEV
Not listed

SSVC (CISA's decision table, applied by EchelonGraph)Track at low or medium mission impact; Attend at high (mission-essential systems).

An upstream fix is merged but not yet in a tagged release. Restrict network exposure of the affected system or apply the vendor's mitigation within your standard update timelines at low or medium mission impact and sooner than that at high until it ships, then apply the release.

Exploitation public PoC (CISA Vulnrichment) · Automatable yes (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE. Mission impact is CISA's Mission & Well-being decision point, and only you can judge it. CISA's table makes it high when Mission Prevalence is Essential — the vulnerable component "directly provides capabilities that constitute at least one MEF for at least one entity" (MEF: mission essential function) — or when Public Well-Being Impact is Irreversible: "multiple fatalities are likely", the cyber-physical system "is likely lost or destroyed", "extreme or serious externalities" are imposed on other parties, or social systems such as elections or the financial grid "are destabilized and potentially collapse". CISA's decision table

BOD 26-04 (CISA's remediation timeline, Table 1)14 days if the affected system is publicly exposed; 60 days if it is not.

In CISA KEV no (CISA's KEV catalog) · Automatable yes (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). Whether your system is publicly exposed is yours to answer. BOD 26-04 binds US Federal Civilian Executive Branch agencies; for anyone else it is CISA's published timeline, a reference rather than an obligation. The directive · how EchelonGraph applies it

Published

April 20, 2026

Last Modified

April 22, 2026

Advisory Details (5)

Auto-updated Aug 3, 2026
Upstream fix merged — awaiting tagged release. Sources: github_commit, github_pr.
GitHub pull request

fix: wrap remaining blocking calls with asyncio.to_thread to prevent DoS

Upstream fix in progress (PR #3835 · lm-sys/FastChat, state=open)

https://github.com/lm-sys/FastChat/pull/3835
Web page

[Security] Denial of Service via Blocking Event Loop in Model Workers (Incomplete Fix for ff66426) · Issue #3833 · lm-sys/FastChat · GitHub

https://github.com/lm-sys/FastChat/issues/3833
GitHub commit

commit c9e84b89c91d (lm-sys/FastChat)

Fix landed in lm-sys/FastChat commit c9e84b89c91d — awaiting tagged release

https://github.com/lm-sys/FastChat/commit/c9e84b89c91d45191dc24466888de526fa04cf33
Web page

GitHub - lm-sys/FastChat: An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena. · GitHub

https://github.com/lm-sys/FastChat/
Web page

Denial of Service via Blocking Event Loop in Model Workers (Incomplete Fix for ff66426) · GitHub

https://gist.github.com/YLChen-007/87216a2d97a882d619e11dc67cd473b5

Patch Availability(1)

Vendor / EcosystemFix (by version range) / PatchReleasedSource
pipfschat—ghsa

Patches are aggregated from vendor advisories (Red Hat, Microsoft, Cisco, GitHub) and package ecosystems (OSV, GHSA). Multiple rows for the same upstream release have been deduplicated.

Affected Packages

(1 across 1 ecosystem)
PyPI(1)
PackageVulnerable rangeFix by version rangeDependents
fschat0.1.1 ... 0.2.9 (34 versions)
  • every version through 0.2.26: no fix on record
—

Weakness Classification(2)

MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.

Data Freshness Timeline

(refreshed 12× in last 7d / 30× in last 30d)

Each row is a time one of our pipelines fetched, updated or re-scored this CVE. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. An arrow marks a change the record states ("CVSS v3 → 9.1"); EPSS and GHSA rows show the values recorded at that time, not what changed (EPSS values are rounded; hover one for the exact figures). Most recent first.

Showing the most recent 97 of 207 refreshes on record for this CVE.

A repeat, a row identical to one the same pipeline wrote less than 10 seconds earlier, is not a separate refresh and is not counted. 3 repeat rows among the latest 100 are merged into the row they repeat. The 110 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-10-13 16:35 UTCEPSS rescoreEPSS 0.7% · 53rd percentile
  2. 2026-10-12 16:34 UTCEPSS rescoreEPSS 0.7% · 53rd percentile
  3. 2026-10-12 15:46 UTCEG score recompute
  4. 2026-10-11 19:31 UTCEG score recompute
  5. 2026-10-11 16:46 UTCEG score recompute
  6. 2026-10-11 14:07 UTCEG score recompute
  7. 2026-10-11 13:49 UTCEPSS rescoreEPSS 0.7% · 53rd percentile
  8. 2026-10-10 20:00 UTCEPSS rescoreEPSS 0.7% · 53rd percentile
  9. 2026-10-10 18:55 UTCOSV refresh
  10. 2026-10-09 20:07 UTCEPSS rescoreEPSS 0.7% · 53rd percentile
  11. 2026-10-08 17:13 UTCEPSS rescoreEPSS 0.7% · 53rd percentile
  12. 2026-10-07 23:48 UTCEPSS rescoreEPSS 0.7% · 53rd percentile
  13. 2026-10-06 15:18 UTCEPSS rescoreEPSS 0.7% · 53rd percentile
  14. 2026-10-05 17:43 UTCEPSS rescoreEPSS 0.7% · 53rd percentile
  15. 2026-10-04 23:22 UTCEPSS rescoreEPSS 0.7% · 53rd percentile
  16. 2026-10-03 14:26 UTCEPSS rescoreEPSS 0.7% · 53rd percentile
  17. 2026-10-02 17:56 UTCEPSS rescoreEPSS 0.7% · 53rd percentile
  18. 2026-10-01 19:50 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  19. 2026-09-30 15:03 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  20. 2026-09-28 13:52 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  21. 2026-09-27 13:48 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  22. 2026-09-26 15:59 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  23. 2026-09-23 17:54 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  24. 2026-09-21 21:09 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  25. 2026-09-21 06:19 UTCOSV refresh
Show 72 more
  1. 2026-09-20 20:16 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  2. 2026-09-18 19:28 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  3. 2026-09-16 14:08 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  4. 2026-09-16 05:15 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  5. 2026-09-15 03:12 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  6. 2026-09-12 15:02 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  7. 2026-09-11 14:53 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  8. 2026-09-10 09:35 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  9. 2026-09-08 22:01 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  10. 2026-09-07 16:01 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  11. 2026-09-06 13:47 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  12. 2026-09-05 15:31 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  13. 2026-09-04 05:07 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  14. 2026-09-02 14:12 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  15. 2026-09-02 03:40 UTCOSV refresh
  16. 2026-09-01 13:54 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  17. 2026-09-01 04:40 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  18. 2026-08-30 19:17 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  19. 2026-08-30 01:22 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  20. 2026-08-28 21:42 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  21. 2026-08-26 14:47 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  22. 2026-08-25 13:49 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  23. 2026-08-23 00:19 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  24. 2026-08-21 23:49 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  25. 2026-08-20 22:56 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  26. 2026-08-19 17:04 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  27. 2026-08-18 13:49 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  28. 2026-08-17 13:47 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  29. 2026-08-16 14:56 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  30. 2026-08-16 06:25 UTCEG score recompute
  31. 2026-08-16 06:25 UTCGHSA enrichmentGHSA-5h65-jx66-j7p5 · GitHub CVSS 5.3
  32. 2026-08-16 02:15 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  33. 2026-08-15 02:25 UTCEG score recompute
  34. 2026-08-15 02:25 UTCGHSA enrichmentGHSA-5h65-jx66-j7p5 · GitHub CVSS 5.3
  35. 2026-08-15 01:31 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  36. 2026-08-14 04:34 UTCEG score recompute
  37. 2026-08-14 04:34 UTCGHSA enrichmentGHSA-5h65-jx66-j7p5 · GitHub CVSS 5.3
  38. 2026-08-13 22:00 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  39. 2026-08-12 22:28 UTCEG score recompute
  40. 2026-08-12 22:28 UTCGHSA enrichmentGHSA-5h65-jx66-j7p5 · GitHub CVSS 5.3
  41. 2026-08-12 13:51 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  42. 2026-08-12 00:37 UTCEG score recompute
  43. 2026-08-12 00:37 UTCGHSA enrichmentGHSA-5h65-jx66-j7p5 · GitHub CVSS 5.3
  44. 2026-08-11 02:31 UTCEG score recompute
  45. 2026-08-11 02:31 UTCGHSA enrichmentGHSA-5h65-jx66-j7p5 · GitHub CVSS 5.3
  46. 2026-08-11 00:00 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  47. 2026-08-10 01:41 UTCEG score recompute
  48. 2026-08-10 01:41 UTCGHSA enrichmentGHSA-5h65-jx66-j7p5 · GitHub CVSS 5.3
  49. 2026-08-09 13:47 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  50. 2026-08-09 03:49 UTCEG score recompute
  51. 2026-08-09 03:49 UTCGHSA enrichmentGHSA-5h65-jx66-j7p5 · GitHub CVSS 5.3
  52. 2026-08-08 16:37 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  53. 2026-08-07 19:00 UTCEG score recompute
  54. 2026-08-07 19:00 UTCGHSA enrichmentGHSA-5h65-jx66-j7p5 · GitHub CVSS 5.3
  55. 2026-08-06 21:09 UTCEG score recompute
  56. 2026-08-06 21:09 UTCGHSA enrichmentGHSA-5h65-jx66-j7p5 · GitHub CVSS 5.3
  57. 2026-08-06 13:47 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  58. 2026-08-05 23:15 UTCEG score recompute
  59. 2026-08-05 23:15 UTCGHSA enrichmentGHSA-5h65-jx66-j7p5 · GitHub CVSS 5.3
  60. 2026-08-05 19:17 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  61. 2026-08-04 15:10 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  62. 2026-08-04 10:39 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  63. 2026-08-03 21:27 UTCEG score recompute
  64. 2026-08-03 21:27 UTCGHSA enrichmentGHSA-5h65-jx66-j7p5 · GitHub CVSS 5.3
  65. 2026-08-03 10:36 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  66. 2026-08-02 12:57 UTCEG score recompute
  67. 2026-08-02 12:57 UTCGHSA enrichmentGHSA-5h65-jx66-j7p5 · GitHub CVSS 5.3
  68. 2026-08-02 02:27 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  69. 2026-08-01 04:16 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  70. 2026-07-30 16:28 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  71. 2026-07-30 01:30 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  72. 2026-07-28 15:37 UTCEPSS rescoreEPSS 0.6% · 46th percentile

Related CVEs(same product + same CWE)

Frequently asked(5)

What is CVE-2026-6607?
CVE-2026-6607 is a medium-severity vulnerability; its CVE record was published on April 20, 2026. A security vulnerability has been detected in lm-sys fastchat up to 0.2.36. This issue affects the function apigenerate of the component Worker API Endpoint. The manipulation leads to resource consumption. The attack can be initiated remotely. The exploit has been disclosed publicly and may be…
When was the CVE record for CVE-2026-6607 published?
The CVE record for CVE-2026-6607 was published on April 20, 2026. That is the record's publication date; the vulnerability itself may have been made public earlier. EchelonGraph's copy of the record carries a last-modified date of April 22, 2026; the record at its source may have been updated since.
Is CVE-2026-6607 actively exploited?
CVE-2026-6607 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.7% probability of exploitation in the next 30 days (53rd percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-6607?
CVE-2026-6607 has a CVSS v3 base score of 5.3 (NVD).
How do I remediate CVE-2026-6607?
An upstream fix for CVE-2026-6607 has been merged but is not yet in a tagged release. Until it ships, restrict network exposure of the affected system or apply the vendor's mitigation, then update to the release that contains the fix.

Dependency Blast Radius

See which npm, PyPI, Go, and Maven packages are affected by CVE-2026-6607

Explore →

Is Your Infrastructure Affected by CVE-2026-6607?

EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.

Book a Demo →Browse All CVEs