CVE-2024-34359

CRITICALNVD 9.69.6
EchelonGraph scoreMEDIUM confidence

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

This critical-severity CVE scores 9.6 under NVD CVSS v3. EPSS exploit probability: 26% (97th percentile of EPSS-scored CVEs). No GitHub Security Advisory CVSS is on record for this CVE.

Triggered by: Headline CVSS from NVD CVSS v3
Sources: EPSS, NVD CVSS v3
Elevated
9.6EG
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).
  • CISA's Vulnrichment rates exploitation as PoC; EchelonGraph holds no exploit-code reference for it
CISA-KEV: Not listedEPSS PROB: 26%CVSS: 9.6Exploit: No code on recordExposed services: Not assessed

A fix is available — apply it.

llama-cpp-python is the Python bindings for llama.cpp. llama-cpp-python depends on class Llama in llama.py to load .gguf llama.cpp or Latency Machine Learning Models. The __init__ constructor built in the Llama takes several parameters to configure the loading and running of the model. Other than NUMA, LoRa settings, loading tokenizers, and hardware settings, __init__ also loads the chat template from targeted .gguf 's Metadata and furtherly parses it to llama_chat_format.Jinja2ChatFormatter.to_chat_handler() to construct the self.chat_handler for this model. Nevertheless, Jinja2ChatFormatter parse the chat template within the Metadate with sandbox-less jinja2.Environment, which is furthermore rendered in __call__ to construct the prompt of interaction. This allows jinja2 Server Side Template Injection which leads to remote code execution by a carefully constructed payload.

CVSS v3
9.6
EG Score
9.6CRITICALmedium confidence
EG Risk
59
EG Risk 59/100

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)
Severity96% × 45%
Impact severity (EG Severity): CVSS 9.6 of 10. Never the KEV-floored or EPSS-lifted EG Score.
Exploitation40% × 40%
EchelonGraph's fixed weight for EG-KEV Tier 3 (Elevated): a constant, not a probability.
Automatability0% × 15%
CISA's SSVC Automatable value: no (Vulnrichment).
SSVC (CISA's decision table, applied by EchelonGraph): Track at low, Track* at medium and Attend at high mission impact.
Exploitation public PoC (CISA Vulnrichment) · Automatable no (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
26%
EPSS %ILE
97th
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 (9.6): severity, escalated by confirmed exploitation. This CVE's 9.6 is its impact severity (EG Severity), not escalated.

EG Severity
9.6 CRITICALCVSS-B, impact only: no KEV listing, EPSS or EG-KEV tier raises it.NVD CVSS v3 · CVSS v3.0 or v3.1
EG Likelihood
26% within 30 daysSource: FIRST EPSS (model v2026.06.15, score date 2026-10-20). 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, Track* at medium and Attend at high mission impact.CISA BOD 26-04: 14 days if the affected system is publicly exposed; Fix on system upgrade if it is not.Each input and its source: the SSVC and BOD 26-04 blocks below.

SSVC (CISA's decision table, applied by EchelonGraph)Track at low, Track* at medium and Attend at high mission impact.

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

Exploitation public PoC (CISA Vulnrichment) · Automatable no (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)14 days if the affected system is publicly exposed; Fix on system upgrade if it is not.

In CISA KEV no (CISA's KEV catalog) · Automatable no (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

May 14, 2024

Last Modified

April 15, 2026

Advisory Details (2)

Auto-updated Oct 2, 2026
Patch available. Sources: github_commit, github.
GitHub advisoryMentions a patch (unverified)

Remote Code Execution by Server-Side Template Injection in Model Metadata · Advisory · abetlen/llama-cpp-python · GitHub

https://github.com/abetlen/llama-cpp-python/security/advisories/GHSA-56xg-wfcc-g829
GitHub commit Patch Available

commit b454f40a9a17 (abetlen/llama-cpp-python)

Patch available: abetlen/llama-cpp-python v0.3.34-metal (contains commit b454f40a9a17)

https://github.com/abetlen/llama-cpp-python/commit/b454f40a9a1787b2b5659cd2cb00819d983185df

Affected Packages

(1 across 1 ecosystem)
PyPI(1)
PackageVulnerable rangeFix by version rangeDependents
llama-cpp-python0.2.30 ... 0.2.71 (42 versions)
  • 0.2.30 up to 0.2.72: fixed in 0.2.72
—

Weakness Classification(1)

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

Data Freshness Timeline

(refreshed 13× in last 7d / 37× 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 92 of 190 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. 8 repeat rows among the latest 100 are merged into the row they repeat. The 98 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-10-21 16:29 UTCEPSS rescoreEPSS 26% · 97th percentile
  2. 2026-10-21 13:44 UTCEG score recompute
  3. 2026-10-20 16:30 UTCEPSS rescoreEPSS 26% · 97th percentile
  4. 2026-10-19 16:55 UTCEG score recompute
  5. 2026-10-19 16:29 UTCEPSS rescoreEPSS 26% · 97th percentile
  6. 2026-10-18 18:33 UTCEG score recompute
  7. 2026-10-18 07:15 UTCEG score recompute
  8. 2026-10-17 20:27 UTCEG score recompute
  9. 2026-10-17 16:31 UTCEPSS rescoreEPSS 26% · 97th percentile
  10. 2026-10-16 22:21 UTCEG score recompute
  11. 2026-10-16 16:36 UTCEPSS rescoreEPSS 26% · 97th percentile
  12. 2026-10-15 18:59 UTCEG score recompute
  13. 2026-10-15 16:30 UTCEPSS rescoreEPSS 26% · 97th percentile
  14. 2026-10-14 16:30 UTCEPSS rescoreEPSS 26% · 97th percentile
  15. 2026-10-14 12:45 UTCEG score recompute
  16. 2026-10-13 16:30 UTCEPSS rescoreEPSS 26% · 97th percentile
  17. 2026-10-12 17:54 UTCEG score recompute
  18. 2026-10-11 21:18 UTCEG score recompute
  19. 2026-10-11 16:11 UTCEG score recompute
  20. 2026-10-11 13:46 UTCEPSS rescoreEPSS 26% · 97th percentile
  21. 2026-10-10 19:58 UTCEPSS rescoreEPSS 26% · 97th percentile
  22. 2026-10-09 20:05 UTCEPSS rescoreEPSS 26% · 97th percentile
  23. 2026-10-08 17:07 UTCEPSS rescoreEPSS 26% · 97th percentile
  24. 2026-10-07 23:46 UTCEPSS rescoreEPSS 26% · 97th percentile
  25. 2026-10-07 12:24 UTCOSV refresh
Show 67 more
  1. 2026-10-06 15:15 UTCEPSS rescoreEPSS 26% · 97th percentile
  2. 2026-10-03 14:24 UTCEPSS rescoreEPSS 26% · 97th percentile
  3. 2026-10-01 19:48 UTCEPSS rescoreEPSS 26% · 97th percentile
  4. 2026-09-30 19:45 UTCEG score recompute
  5. 2026-09-30 15:01 UTCEPSS rescoreEPSS 26% · 97th percentile
  6. 2026-09-29 15:17 UTCEPSS rescoreEPSS 26% · 97th percentile
  7. 2026-09-27 13:44 UTCEPSS rescoreEPSS 26% · 97th percentile
  8. 2026-09-26 15:57 UTCEPSS rescoreEPSS 26% · 97th percentile
  9. 2026-09-26 00:23 UTCEPSS rescoreEPSS 26% · 97th percentile
  10. 2026-09-24 14:01 UTCEPSS rescoreEPSS 26% · 97th percentile
  11. 2026-09-23 13:46 UTCEPSS rescoreEPSS 26% · 97th percentile
  12. 2026-09-22 14:46 UTCEPSS rescoreEPSS 26% · 97th percentile
  13. 2026-09-21 20:32 UTCEPSS rescoreEPSS 26% · 97th percentile
  14. 2026-09-19 15:40 UTCEPSS rescoreEPSS 26% · 97th percentile
  15. 2026-09-18 19:26 UTCEPSS rescoreEPSS 26% · 97th percentile
  16. 2026-09-17 18:36 UTCOSV refresh
  17. 2026-09-16 14:06 UTCEPSS rescoreEPSS 27% · 97th percentile
  18. 2026-09-15 03:08 UTCEPSS rescoreEPSS 28% · 98th percentile
  19. 2026-09-12 14:59 UTCEPSS rescoreEPSS 28% · 98th percentile
  20. 2026-09-11 14:51 UTCEPSS rescoreEPSS 28% · 98th percentile
  21. 2026-09-11 09:35 UTCEPSS rescoreEPSS 28% · 98th percentile
  22. 2026-09-07 15:59 UTCEPSS rescoreEPSS 28% · 97th percentile
  23. 2026-09-06 13:46 UTCEPSS rescoreEPSS 28% · 97th percentile
  24. 2026-09-05 15:26 UTCEPSS rescoreEPSS 28% · 98th percentile
  25. 2026-09-04 13:59 UTCEPSS rescoreEPSS 28% · 97th percentile
  26. 2026-09-04 05:05 UTCEPSS rescoreEPSS 28% · 97th percentile
  27. 2026-09-02 14:10 UTCEPSS rescoreEPSS 28% · 97th percentile
  28. 2026-08-30 19:15 UTCEPSS rescoreEPSS 28% · 97th percentile
  29. 2026-08-30 01:20 UTCEPSS rescoreEPSS 28% · 98th percentile
  30. 2026-08-29 18:43 UTCOSV refresh
  31. 2026-08-28 21:39 UTCEPSS rescoreEPSS 28% · 98th percentile
  32. 2026-08-27 14:23 UTCEPSS rescoreEPSS 28% · 97th percentile
  33. 2026-08-26 14:44 UTCEPSS rescoreEPSS 28% · 97th percentile
  34. 2026-08-25 13:47 UTCEPSS rescoreEPSS 28% · 97th percentile
  35. 2026-08-24 14:15 UTCEPSS rescoreEPSS 28% · 97th percentile
  36. 2026-08-23 00:18 UTCEPSS rescoreEPSS 28% · 97th percentile
  37. 2026-08-21 23:47 UTCEPSS rescoreEPSS 28% · 97th percentile
  38. 2026-08-20 22:53 UTCEPSS rescoreEPSS 28% · 97th percentile
  39. 2026-08-19 17:02 UTCEPSS rescoreEPSS 28% · 97th percentile
  40. 2026-08-18 13:46 UTCEPSS rescoreEPSS 28% · 97th percentile
  41. 2026-08-16 14:54 UTCEPSS rescoreEPSS 28% · 97th percentile
  42. 2026-08-16 02:13 UTCEPSS rescoreEPSS 28% · 97th percentile
  43. 2026-08-15 01:28 UTCEPSS rescoreEPSS 28% · 97th percentile
  44. 2026-08-13 21:59 UTCEPSS rescoreEPSS 28% · 97th percentile
  45. 2026-08-13 05:42 UTCOSV refresh
  46. 2026-08-12 13:49 UTCEPSS rescoreEPSS 28% · 97th percentile
  47. 2026-08-11 13:40 UTCEPSS rescoreEPSS 28% · 97th percentile
  48. 2026-08-10 23:58 UTCEPSS rescoreEPSS 28% · 97th percentile
  49. 2026-08-08 16:35 UTCEPSS rescoreEPSS 28% · 97th percentile
  50. 2026-08-07 16:25 UTCEPSS rescoreEPSS 28% · 97th percentile
  51. 2026-08-06 13:45 UTCEPSS rescoreEPSS 28% · 97th percentile
  52. 2026-08-05 19:16 UTCEPSS rescoreEPSS 28% · 97th percentile
  53. 2026-08-04 10:36 UTCEPSS rescoreEPSS 28% · 97th percentile
  54. 2026-08-03 10:34 UTCEPSS rescoreEPSS 28% · 97th percentile
  55. 2026-08-02 02:25 UTCEPSS rescoreEPSS 28% · 97th percentile
  56. 2026-08-01 04:14 UTCEPSS rescoreEPSS 28% · 97th percentile
  57. 2026-07-30 16:26 UTCEPSS rescoreEPSS 28% · 97th percentile
  58. 2026-07-30 01:29 UTCEPSS rescoreEPSS 28% · 97th percentile
  59. 2026-07-28 15:34 UTCEPSS rescoreEPSS 28% · 97th percentile
  60. 2026-07-28 13:51 UTCOSV refresh
  61. 2026-07-26 14:53 UTCEPSS rescoreEPSS 28% · 97th percentile
  62. 2026-07-25 14:16 UTCEPSS rescoreEPSS 28% · 97th percentile
  63. 2026-07-24 14:16 UTCEPSS rescoreEPSS 28% · 97th percentile
  64. 2026-07-23 14:17 UTCEPSS rescoreEPSS 28% · 97th percentile
  65. 2026-07-23 02:37 UTCEG score recompute
  66. 2026-07-22 14:07 UTCEPSS rescoreEPSS 28% · 97th percentile
  67. 2026-07-21 15:23 UTCEPSS rescoreEPSS 28% · 97th percentile

Frequently asked(5)

What is CVE-2024-34359?
CVE-2024-34359 is a critical-severity vulnerability; its CVE record was published on May 14, 2024. llama-cpp-python is the Python bindings for llama.cpp. llama-cpp-python depends on class Llama in llama.py to load .gguf llama.cpp or Latency Machine Learning Models. The init constructor built in the Llama takes several parameters to configure the loading and running of the model. Other than NUMA,…
When was the CVE record for CVE-2024-34359 published?
The CVE record for CVE-2024-34359 was published on May 14, 2024. 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 15, 2026; the record at its source may have been updated since.
Is CVE-2024-34359 actively exploited?
CVE-2024-34359 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 26% probability of exploitation in the next 30 days (97th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2024-34359?
CVE-2024-34359 has a CVSS v3 base score of 9.6 (NVD).
How do I remediate CVE-2024-34359?
A fix for CVE-2024-34359 is available: update to the fixed version the vendor names in its advisory.

Dependency Blast Radius

See which npm, PyPI, Go, and Maven packages are affected by CVE-2024-34359

Explore →

Is Your Infrastructure Affected by CVE-2024-34359?

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