CVE-2025-66455

CRITICALPre-NVD 9.89.8
EchelonGraph scoreMEDIUM confidence

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

Score 9.8 from GitHub Security Advisory (severity: CRITICAL) published 2026-09-18. A secondary CVSS source baseline 9.8; sources differ by 0.0.

Triggered by: GitHub Security Advisory CVSS
Sources: EPSS, GitHub Security Advisory, a secondary CVSS source
Trending — 3 sources updated this week

Also known asEUVD-2025-210969 (ENISA EUVD) · GHSA-2vh9-42vm-xmv2 (GitHub Security Advisories)Source: ENISA EUVD

9.8EG
EchelonGraph verdictPlan a fixRemediate within your standard update timelines at low or medium mission impact and sooner than that at high (the SSVC decision on this page).
  • High severity, but no confirmed exploitation yet
CISA-KEV: Not listedEPSS PROB: 1.3%CVSS: 9.8Exploit: None knownExposed services: Not assessed

A fix is available — apply it.

LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.2 and prior to version 0.16.0, LMDeploy's PyTorch DistServe/PD-disaggregation control plane used recv_pyobj() to deserialize messages received through a ZeroMQ PULL socket. PyZMQ implements recv_pyobj() using Python pickle deserialization, which can execute arbitrary code while reconstructing an object. The peer address used by the receiver was supplied through the POST /distserve/p2p_connect HTTP endpoint. An attacker who could reach an affected DistServe API server could cause the server to connect to an attacker-controlled ZeroMQ endpoint and deserialize a crafted pickle payload. API-key authentication is not enabled unless the operator explicitly configures it. As a result, affected DistServe deployments without API keys allowed unauthenticated remote code execution with the privileges of the LMDeploy serving process. This issue affects the PyTorch backend when PD-disaggregation/DistServe is enabled. Ordinary deployments that do not use the affected disaggregated-serving path do not expose this data flow. The fix was released in LMDeploy 0.16.0. Users who cannot upgrade immediately should prevent untrusted clients from reaching /distserve/* endpoints, restrict the DistServe HTTP and ZeroMQ control planes to trusted cluster networks, configure API-key authentication, and block arbitrary outbound ZeroMQ connections from serving nodes. These measures reduce exposure but do not make pickle deserialization safe.

CVSS v3
9.8
EG Score
9.8CRITICALmedium confidence
EG Risk
60
EG Risk 60/100

EG Risk is EchelonGraph's 0–100 priority score. It fuses impact severity (EG Severity, the CVSS base score, never the KEV-floored or EPSS-lifted EG Score) with real-world exploitation and automatability, under weights EchelonGraph set by hand, so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner.

How it’s computed (value × EchelonGraph’s weight)
Severity98% × 45%
Impact severity (EG Severity): CVSS 9.8 of 10. Never the KEV-floored or EPSS-lifted EG Score.
Exploitation1.3% × 40%
FIRST EPSS: the 30-day exploitation probability when EchelonGraph scored this CVE.
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 none (CISA Vulnrichment) · Automatable yes (CISA Vulnrichment) · Technical impact total (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: A fix is available. Apply it within your standard update timelines at low or medium mission impact and sooner than that at high.
EPSS PROB
1.3%
EPSS %ILE
69th
KEV
Not listed

What the EG score is made of (scorer v4.0: the three questions the 0–10 score mixes, published apart · methodology)

The EG score (9.8): severity, escalated by confirmed exploitation. This CVE's 9.8 is its impact severity (EG Severity), not escalated.

EG Severity
9.8 CRITICALCVSS-B, impact only: no KEV listing, EPSS or EG-KEV tier raises it.GitHub Security Advisory CVSS
EG Likelihood
1.3% within 30 daysSource: FIRST EPSS (model v2026.06.15, score date 2026-11-02). FIRST's exploitation probability, not an EchelonGraph model.
Confirmed exploitation
None on record (CISA KEV, EG-KEV Tier 1)Reported apart from the likelihood: an observed fact, not a probability.
EG Priority
SSVC Track at medium mission impactTrack at low or medium mission impact; Attend at high (mission-essential systems).CISA BOD 26-04: 3 days if the affected system is publicly exposed; 60 days if it is not.Each input and its source, and whom BOD 26-04 binds: the SSVC and BOD 26-04 blocks below.

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

A fix is available. Apply it within your standard update timelines at low or medium mission impact and sooner than that at high.

Exploitation none (CISA Vulnrichment) · Automatable yes (CISA Vulnrichment) · Technical impact total (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)3 days if the affected system is publicly exposed; 60 days if it is not.

The score's inputs: In CISA KEV no (CISA's KEV catalog) · Automatable yes (CISA Vulnrichment) · Technical impact total (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

September 18, 2026

Last Modified

October 14, 2026

Advisory Details (3)

Auto-updated Oct 30, 2026
Patch available. Sources: github_commit, github_release, github.
GitHub advisoryMentions a patch (unverified)

Unauthenticated remote code execution via pickle deserialization in DistServe P2P connection · Advisory · InternLM/lmdeploy · GitHub

https://github.com/InternLM/lmdeploy/security/advisories/GHSA-2vh9-42vm-xmv2
GitHub release Patch Available

v0.16.0

Patch available: InternLM/lmdeploy v0.16.0

https://github.com/InternLM/lmdeploy/releases/tag/v0.16.0
GitHub commit

commit f05b4ad8bf2e (InternLM/lmdeploy)

Fix landed in InternLM/lmdeploy commit f05b4ad8bf2e — awaiting tagged release

https://github.com/InternLM/lmdeploy/commit/f05b4ad8bf2e2d84101a1d63b3c44fadd99223b2

Vendor Advisories for CVE-2025-66455(1)

These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.

Patch Availability(1)

Vendor / EcosystemFix (by version range) / PatchReleasedSource
piplmdeploy @ 0.16.0 (fixes >= 0.9.2, < 0.16.0)—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
lmdeploy0.10.0 ... 0.9.2.post1 (14 versions)
  • 0.9.2 up to 0.16.0: fixed in 0.16.0
—

Weakness Classification(1)

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

Data Freshness Timeline

(refreshed 17× in last 7d / 66× 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 98 of 99 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. 2 repeat rows among the latest 100 are merged into the row they repeat. The 1 oldest row on record is not shown and was not checked, so the counts can still include repeats.

  1. 2026-11-03 16:45 UTCEPSS rescoreEPSS 1.3% · 69th percentile
  2. 2026-11-03 11:32 UTCEG score recompute
  3. 2026-11-03 11:32 UTCGHSA enrichmentGHSA-2vh9-42vm-xmv2 · GitHub severity CRITICAL · GitHub CVSS 9.8
  4. 2026-11-02 16:43 UTCEPSS rescoreEPSS 1.3% · 69th percentile
  5. 2026-11-02 12:20 UTCEG score recompute
  6. 2026-11-02 12:20 UTCGHSA enrichmentGHSA-2vh9-42vm-xmv2 · GitHub severity CRITICAL · GitHub CVSS 9.8
  7. 2026-11-01 16:33 UTCEPSS rescoreEPSS 1.3% · 69th percentile
  8. 2026-11-01 13:10 UTCGHSA enrichmentGHSA-2vh9-42vm-xmv2 · GitHub severity CRITICAL · GitHub CVSS 9.8
  9. 2026-11-01 08:01 UTCGHSA enrichmentGHSA-2vh9-42vm-xmv2 · GitHub severity CRITICAL · GitHub CVSS 9.8
  10. 2026-11-01 08:01 UTCEG score recompute
  11. 2026-10-31 16:31 UTCEPSS rescoreEPSS 1.3% · 69th percentile
  12. 2026-10-31 13:59 UTCEG score recompute
  13. 2026-10-30 16:33 UTCEPSS rescoreEPSS 1.3% · 69th percentile
  14. 2026-10-30 14:48 UTCEG score recompute
  15. 2026-10-29 16:32 UTCEPSS rescoreEPSS 1.3% · 69th percentile
  16. 2026-10-29 15:37 UTCEG score recompute
  17. 2026-10-28 16:30 UTCEPSS rescoreEPSS 1.3% · 69th percentile
  18. 2026-10-27 16:57 UTCEG score recompute
  19. 2026-10-27 16:30 UTCEPSS rescoreEPSS 1.3% · 69th percentile
  20. 2026-10-26 17:44 UTCEG score recompute
  21. 2026-10-26 16:30 UTCEPSS rescoreEPSS 1.3% · 69th percentile
  22. 2026-10-25 18:01 UTCEG score recompute
  23. 2026-10-25 16:31 UTCEPSS rescoreEPSS 1.3% · 69th percentile
  24. 2026-10-25 16:08 UTCEG score recompute
  25. 2026-10-24 18:18 UTCEG score recompute
Show 73 more
  1. 2026-10-24 16:31 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  2. 2026-10-23 19:09 UTCEG score recompute
  3. 2026-10-23 16:31 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  4. 2026-10-22 19:54 UTCEG score recompute
  5. 2026-10-22 16:33 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  6. 2026-10-21 20:44 UTCEG score recompute
  7. 2026-10-21 16:31 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  8. 2026-10-20 21:31 UTCEG score recompute
  9. 2026-10-20 16:31 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  10. 2026-10-19 22:21 UTCEG score recompute
  11. 2026-10-19 16:31 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  12. 2026-10-18 21:13 UTCEG score recompute
  13. 2026-10-18 05:19 UTCEG score recompute
  14. 2026-10-17 22:02 UTCEG score recompute
  15. 2026-10-17 16:33 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  16. 2026-10-16 22:51 UTCEG score recompute
  17. 2026-10-16 16:39 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  18. 2026-10-15 19:51 UTCEG score recompute
  19. 2026-10-15 16:31 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  20. 2026-10-14 16:31 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  21. 2026-10-14 03:15 UTCEG score recompute
  22. 2026-10-13 16:33 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  23. 2026-10-12 16:48 UTCEG score recompute
  24. 2026-10-12 16:33 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  25. 2026-10-11 20:19 UTCEG score recompute
  26. 2026-10-11 18:35 UTCEG score recompute
  27. 2026-10-11 15:09 UTCEG score recompute
  28. 2026-10-11 13:47 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  29. 2026-10-11 12:07 UTCEG score recompute
  30. 2026-10-10 23:45 UTCEG score recompute
  31. 2026-10-10 19:59 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  32. 2026-10-09 22:49 UTCEG score recompute
  33. 2026-10-09 20:06 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  34. 2026-10-08 17:25 UTCEG score recompute
  35. 2026-10-08 17:10 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  36. 2026-10-08 02:17 UTCEG score recompute
  37. 2026-10-07 23:47 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  38. 2026-10-06 16:30 UTCEG score recompute
  39. 2026-10-06 15:17 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  40. 2026-10-05 20:06 UTCEG score recompute
  41. 2026-10-05 17:42 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  42. 2026-10-04 23:29 UTCEG score recompute
  43. 2026-10-04 23:21 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  44. 2026-10-03 14:26 UTCEG score recompute
  45. 2026-10-03 14:25 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  46. 2026-10-02 17:58 UTCEG score recompute
  47. 2026-10-01 21:29 UTCEG score recompute
  48. 2026-10-01 19:49 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  49. 2026-09-30 16:56 UTCEG score recompute
  50. 2026-09-30 15:02 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  51. 2026-09-29 19:19 UTCEG score recompute
  52. 2026-09-29 15:20 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  53. 2026-09-28 22:22 UTCEG score recompute
  54. 2026-09-28 14:13 UTCEG score recompute
  55. 2026-09-28 13:50 UTCEPSS rescoreEPSS 0.7% · 50th percentile
  56. 2026-09-27 17:50 UTCEG score recompute
  57. 2026-09-26 17:15 UTCEG score recompute
  58. 2026-09-26 15:58 UTCEPSS rescoreEPSS 0.7% · 50th percentile
  59. 2026-09-26 00:46 UTCEG score recompute
  60. 2026-09-24 15:04 UTCEG score recompute
  61. 2026-09-24 14:02 UTCEPSS rescoreEPSS 0.7% · 50th percentile
  62. 2026-09-23 14:50 UTCEG score recompute
  63. 2026-09-23 13:47 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  64. 2026-09-22 18:27 UTCEG score recompute
  65. 2026-09-21 22:03 UTCEG score recompute
  66. 2026-09-20 21:36 UTCEG score recompute
  67. 2026-09-20 20:15 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  68. 2026-09-19 16:58 UTCEG score recompute
  69. 2026-09-19 15:42 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  70. 2026-09-18 20:31 UTCEG score recompute
  71. 2026-09-18 19:59 UTCEG score recompute
  72. 2026-09-18 18:27 UTCEG score recompute
  73. 2026-09-18 17:19 UTCEG score recomputeFirst assessed: 9.8 CRITICAL

Frequently asked(5)

What is CVE-2025-66455?
CVE-2025-66455 is a critical-severity vulnerability; its CVE record was published on September 18, 2026. LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.2 and prior to version 0.16.0, LMDeploy's PyTorch DistServe/PD-disaggregation control plane used recv_pyobj() to deserialize messages received through a ZeroMQ PULL socket. PyZMQ implements…
When was the CVE record for CVE-2025-66455 published?
The CVE record for CVE-2025-66455 was published on September 18, 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 October 14, 2026; the record at its source may have been updated since.
Is CVE-2025-66455 actively exploited?
CVE-2025-66455 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 1.3% probability of exploitation in the next 30 days (69th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2025-66455?
CVE-2025-66455 has a CVSS base score of 9.8 (a secondary CVSS source that NVD displays; NVD's own analysis pending).
How do I remediate CVE-2025-66455?
A fix for CVE-2025-66455 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2025-66455 are linked in the Vendor Advisories panel on this page.

Dependency Blast Radius

See which npm, PyPI, Go, and Maven packages are affected by CVE-2025-66455

Explore →

Is Your Infrastructure Affected by CVE-2025-66455?

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