CVE-2026-105192

CRITICALPre-NVD 9.89.8
EchelonGraph scoreHIGH confidence

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

Score 9.8 from GitHub Security Advisory (severity: CRITICAL) published 2026-10-16. 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-2026-94261 (ENISA EUVD) · GHSA-vv44-hjm2-qw2f (GitHub Security Advisories) · GHSA-w5f2-9q9c-ff4h (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: 1.0%CVSS: 9.8Exploit: None knownExposed services: Not assessed

A fix is available — apply it.

Fixed versions, as the CVE record's CNA (JFrog) states them: "Upgrade to LMCache 0.5.6 or later."

LMCache multiprocess mode, also called distributed mode, opens an unauthenticated ZeroMQ ROUTER so worker processes can register and share KV cache blocks. Messages on that socket are msgpack. Extension code 1 is passed to DeviceIPCWrapper.Deserialize, which calls pickle.loads, while the server is still decoding request arguments and before the handler runs. A single unauthenticated ZMQ DEALER message to the transport port (default 5555) therefore executes code as the user the LMCache process runs as. Official container images run that process as root. The transport binds to localhost unless the operator sets a routable address with --host, which is how multi-node deployments let peers connect. The decode path shipped in v0.3.9 and is present through v0.5.5, including the v0.5.6 release candidates. v0.5.6, published on 2026-10-14, removes pickle.loads from this path.

CVSS v3
9.8
EG Score
9.8CRITICALhigh 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.
Exploitation1.0% × 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
1.0%
EPSS %ILE
63rd
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
1.0% within 30 daysSource: FIRST EPSS (model v2026.06.15, score date 2026-11-01). 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

October 7, 2026

Last Modified

October 29, 2026

Advisory Details (10)

Auto-updated Oct 30, 2026
🔬 Proof of concept available. Patch available. Sources: github_pr, github_release, github.
Web page

lmcache · PyPI

https://pypi.org/project/lmcache/
GitHub advisoryMentions a patch (unverified)🟡 PoC Available

Remote code execution via unsafe deserialization in multiprocess mode transport · Advisory · LMCache/LMCache · GitHub

https://github.com/LMCache/LMCache/security/advisories/GHSA-w5f2-9q9c-ff4h
GitHub release Patch Available

v0.5.6

Patch available: LMCache/LMCache v0.5.6

https://github.com/LMCache/LMCache/releases/tag/v0.5.6
GitHub pull request

feat(docker): run official images as a non-root user by default

Fix merged in LMCache/LMCache PR #5685 on 2026-10-14 — awaiting tagged release

https://github.com/LMCache/LMCache/pull/5685
GitHub pull request

fix(mp): bind example Kubernetes deployment to localhost

Fix merged in LMCache/LMCache PR #5684 on 2026-10-13 — awaiting tagged release

https://github.com/LMCache/LMCache/pull/5684
GitHub pull request

[Security][MP] Remove pickle from device IPC descriptors (CVE-2026-105192)

Fix merged in LMCache/LMCache PR #5644 on 2026-10-12 — awaiting tagged release

https://github.com/LMCache/LMCache/pull/5644
Web page

LMCache/lmcache/v1/platform/base/ipc_wrapper.py at v0.5.5 · LMCache/LMCache · GitHub

https://github.com/LMCache/LMCache/blob/v0.5.5/lmcache/v1/platform/base/ipc_wrapper.py
Web page

LMCache/lmcache/v1/multiprocess/custom_types.py at v0.3.9 · LMCache/LMCache · GitHub

https://github.com/LMCache/LMCache/blob/v0.3.9/lmcache/v1/multiprocess/custom_types.py
Web page

GitHub - LMCache/LMCache: LMCache: Supercharge Your LLM with the Fastest KV Cache Layer · GitHub

https://github.com/LMCache/LMCache
Web page

An Update on CVE-2026-105192 – LMCache Blog

https://blog.lmcache.ai/en/2026/10/13/an-update-on-cve-2026-105192/

Vendor Advisories for CVE-2026-105192(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
piplmcache @ 0.5.6 (fixes >= 0.3.9, < 0.5.6)—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
lmcache0.3.10 ... 0.5.6rc5 (53 versions)
  • 0.3.9 up to 0.5.6: fixed in 0.5.6
—

Weakness Classification(2)

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

Data Freshness Timeline

(refreshed 18× in last 7d / 98× 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.

  1. 2026-11-02 16:43 UTCEPSS rescoreEPSS 1.0% · 63rd percentile
  2. 2026-11-02 12:52 UTCEG score recompute
  3. 2026-11-02 12:51 UTCGHSA enrichmentGHSA-w5f2-9q9c-ff4h · GitHub severity CRITICAL · GitHub CVSS 9.8
  4. 2026-11-01 16:33 UTCEPSS rescoreEPSS 1.0% · 63rd percentile
  5. 2026-11-01 12:31 UTCGHSA enrichmentGHSA-w5f2-9q9c-ff4h · GitHub severity CRITICAL · GitHub CVSS 9.8
  6. 2026-11-01 08:00 UTCGHSA enrichmentGHSA-w5f2-9q9c-ff4h · GitHub severity CRITICAL · GitHub CVSS 9.8
  7. 2026-11-01 08:00 UTCEG score recompute
  8. 2026-10-31 16:31 UTCEPSS rescoreEPSS 1.0% · 63rd percentile
  9. 2026-10-31 12:09 UTCEG score recompute
  10. 2026-10-30 16:33 UTCEPSS rescoreEPSS 1.0% · 63rd percentile
  11. 2026-10-30 11:47 UTCEG score recompute
  12. 2026-10-29 16:32 UTCEPSS rescoreEPSS 0.8% · 55th percentile
  13. 2026-10-29 11:26 UTCEG score recompute
  14. 2026-10-29 10:28 UTCEG score recompute
  15. 2026-10-28 16:31 UTCEPSS rescoreEPSS 0.8% · 55th percentile
  16. 2026-10-28 16:18 UTCEG score recompute
  17. 2026-10-27 16:31 UTCEPSS rescoreEPSS 0.8% · 55th percentile
  18. 2026-10-27 15:56 UTCEG score recompute
  19. 2026-10-26 16:30 UTCEPSS rescoreEPSS 0.8% · 55th percentile
  20. 2026-10-26 15:32 UTCEG score recompute
  21. 2026-10-25 16:32 UTCEPSS rescoreEPSS 0.8% · 55th percentile
  22. 2026-10-25 14:44 UTCEG score recompute
  23. 2026-10-24 16:32 UTCEPSS rescoreEPSS 0.5% · 40th percentile
  24. 2026-10-24 14:22 UTCEG score recompute
  25. 2026-10-23 16:31 UTCEPSS rescoreEPSS 0.5% · 40th percentile
Show 73 more
  1. 2026-10-23 14:02 UTCEG score recompute
  2. 2026-10-22 16:33 UTCEPSS rescoreEPSS 0.5% · 40th percentile
  3. 2026-10-22 13:40 UTCEG score recompute
  4. 2026-10-21 16:32 UTCEPSS rescoreEPSS 0.5% · 40th percentile
  5. 2026-10-21 13:19 UTCEG score recompute
  6. 2026-10-20 16:31 UTCEPSS rescoreEPSS 0.5% · 40th percentile
  7. 2026-10-20 12:36 UTCEG score recompute
  8. 2026-10-19 16:31 UTCEPSS rescoreEPSS 0.5% · 40th percentile
  9. 2026-10-19 12:13 UTCEG score recompute
  10. 2026-10-18 16:31 UTCEPSS rescoreEPSS 0.5% · 40th percentile
  11. 2026-10-18 05:09 UTCEG score recompute
  12. 2026-10-17 16:33 UTCEPSS rescoreEPSS 0.5% · 40th percentile
  13. 2026-10-17 08:28 UTCEG score recompute
  14. 2026-10-16 16:40 UTCEPSS rescoreEPSS 0.5% · 40th percentile
  15. 2026-10-16 08:05 UTCEG score recompute
  16. 2026-10-16 08:05 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  17. 2026-10-15 16:31 UTCEPSS rescoreEPSS 0.5% · 40th percentile
  18. 2026-10-15 07:08 UTCEG score recompute
  19. 2026-10-15 07:08 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  20. 2026-10-14 16:31 UTCEPSS rescoreEPSS 0.5% · 40th percentile
  21. 2026-10-14 03:01 UTCEG score recompute
  22. 2026-10-14 03:00 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  23. 2026-10-13 16:33 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  24. 2026-10-12 23:06 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  25. 2026-10-12 16:40 UTCEG score recompute
  26. 2026-10-12 16:33 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  27. 2026-10-12 02:10 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  28. 2026-10-11 22:03 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  29. 2026-10-11 20:15 UTCEG score recompute
  30. 2026-10-11 17:56 UTCEG score recompute
  31. 2026-10-11 17:56 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  32. 2026-10-11 13:47 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  33. 2026-10-11 13:42 UTCEG score recompute
  34. 2026-10-11 13:42 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  35. 2026-10-11 09:30 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  36. 2026-10-11 05:19 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  37. 2026-10-11 01:13 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  38. 2026-10-10 21:03 UTCEG score recompute
  39. 2026-10-10 21:03 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  40. 2026-10-10 19:59 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  41. 2026-10-10 16:53 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  42. 2026-10-10 12:42 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  43. 2026-10-10 08:34 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  44. 2026-10-10 04:27 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  45. 2026-10-10 00:21 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  46. 2026-10-09 20:15 UTCEG score recompute
  47. 2026-10-09 20:15 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  48. 2026-10-09 20:06 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  49. 2026-10-09 16:08 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  50. 2026-10-09 12:01 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  51. 2026-10-09 07:54 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  52. 2026-10-09 03:47 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  53. 2026-10-08 23:41 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  54. 2026-10-08 19:35 UTCEG score recompute
  55. 2026-10-08 19:35 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  56. 2026-10-08 17:11 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  57. 2026-10-08 15:13 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  58. 2026-10-08 11:05 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  59. 2026-10-08 06:59 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  60. 2026-10-08 02:52 UTCEG score recompute
  61. 2026-10-08 02:52 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  62. 2026-10-07 23:47 UTCEPSS rescoreEPSS 0.7% · 50th percentile
  63. 2026-10-07 22:46 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  64. 2026-10-07 18:39 UTCEG score recompute
  65. 2026-10-07 18:39 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  66. 2026-10-07 17:58 UTCEG score recompute
  67. 2026-10-07 17:57 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  68. 2026-10-07 16:13 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  69. 2026-10-07 14:29 UTCEG score recompute
  70. 2026-10-07 14:29 UTCGHSA enrichmentGHSA-vv44-hjm2-qw2f · GitHub severity CRITICAL · GitHub CVSS 9.8
  71. 2026-10-07 10:21 UTCEG score recompute
  72. 2026-10-07 09:57 UTCEG score recomputeFirst assessed: 9.8 CRITICAL
  73. 2026-10-07 09:56 UTCMITRE cvelistV5first tracked

Frequently asked(5)

What is CVE-2026-105192?
CVE-2026-105192 is a critical-severity vulnerability; its CVE record was published on October 7, 2026. LMCache multiprocess mode, also called distributed mode, opens an unauthenticated ZeroMQ ROUTER so worker processes can register and share KV cache blocks. Messages on that socket are msgpack. Extension code 1 is passed to DeviceIPCWrapper.Deserialize, which calls pickle.loads, while the server is…
When was the CVE record for CVE-2026-105192 published?
The CVE record for CVE-2026-105192 was published on October 7, 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 29, 2026; the record at its source may have been updated since.
Is CVE-2026-105192 actively exploited?
CVE-2026-105192 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 1.0% probability of exploitation in the next 30 days (63rd percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-105192?
CVE-2026-105192 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-2026-105192?
A fix for CVE-2026-105192 is available: update to the fixed version the vendor names in its advisory. Fixed versions, as the CVE record's CNA (JFrog) states them: "Upgrade to LMCache 0.5.6 or later." The vendor advisories EchelonGraph has for CVE-2026-105192 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-2026-105192

Explore →

Is Your Infrastructure Affected by CVE-2026-105192?

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