CVE-2026-15035

HIGHNVD 7.87.8
EchelonGraph scoreMEDIUM confidence

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

This high-severity CVE scores 7.8 under NVD CVSS v3. EPSS exploit probability: 2.2% (82nd percentile of EPSS-scored CVEs). GitHub Security Advisory CVSS 5.3 is lower than this score; a lower GitHub score revises it only when its advisory is newer than the CVE record's last change, and this advisory (published 2026-07-08) is not newer than that change (2026-07-09), so it does not.

Triggered by: Headline CVSS from NVD CVSS v3
Sources: EPSS, GitHub Security Advisory, NVD CVSS v3
Elevated
7.8EG
EchelonGraph verdictPlan mitigationRemediate within your standard update timelines (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: 2.2%CVSS: 7.8Exploit: No code on recordExposed services: Not assessed

A fix is referenced (a reference tagged "Patch", often a source commit), but no release containing it is confirmed — find the release that contains it; until it is applied, mitigate (WAF / firewall / segmentation).

A vulnerability was found in bentoml OpenLLM 0.6.30. This affects the function async_run_command of the file src/openllm/common.py of the component Model Repository Directory Name Handler. Performing a manipulation of the argument cmd results in command injection. Attacking locally is a requirement. The exploit has been made public and could be used. The project was informed of the problem early through an issue report but has not responded yet.

CVSS v3
7.8
EG Score
7.8HIGHmedium confidence
EG Risk
51
EG Risk 51/100

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)
Severity78% × 45%
The EG Score, 7.8 of 10.
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 or medium mission impact; Track* at high (mission-essential systems).
Exploitation public PoC (CISA Vulnrichment) · Automatable no (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: A fix is referenced, but no release containing it is confirmed. Check the referenced fix and the vendor's advisory for a release that contains it and apply that within your standard update timelines; until then, restrict network exposure of the affected system or apply the vendor's mitigation.
EPSS PROB
2.2%
EPSS %ILE
82nd
KEV
Not listed

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

A fix is referenced, but no release containing it is confirmed. Check the referenced fix and the vendor's advisory for a release that contains it and apply that within your standard update timelines; until then, restrict network exposure of the affected system or apply the vendor's mitigation.

Exploitation public PoC (CISA Vulnrichment) · Automatable no (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)60 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 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

July 8, 2026

Last Modified

July 9, 2026

Advisory Details (3)

Auto-updated Jul 9, 2026
Fix referenced — no release confirmed yet. Sources: github_pr.
GitHub pull request

fix(security): use exec instead of shell in async_run_command (CWE-78)

Upstream fix in progress (PR #1235 · bentoml/OpenLLM, state=open)

https://github.com/bentoml/OpenLLM/pull/1235
Web page

[Security] Shell command injection via malicious model repository directory names · Issue #1229 · bentoml/OpenLLM · GitHub

https://github.com/bentoml/OpenLLM/issues/1229
Web page

GitHub - bentoml/OpenLLM: Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud. · GitHub

https://github.com/bentoml/OpenLLM/

Vendor Advisories for CVE-2026-15035(1)

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

Affected Packages

(1 across 1 ecosystem)
PyPI(1)
PackageVulnerable rangeFix by version rangeDependents
bentoml0.0.1 ... 0.6.3 (41 versions)
  • every version through 0.6.30: no fix on record
—

Weakness Classification(3)

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

Data Freshness Timeline

(refreshed 12× in last 7d / 35× 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 100 of 228 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. None are among the latest 100 rows. The 128 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-10-14 16:32 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  2. 2026-10-13 16:33 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  3. 2026-10-12 16:33 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  4. 2026-10-12 16:33 UTCEG score recompute
  5. 2026-10-11 20:10 UTCEG score recompute
  6. 2026-10-11 17:22 UTCEG score recompute
  7. 2026-10-11 14:55 UTCEG score recompute
  8. 2026-10-11 13:48 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  9. 2026-10-10 19:59 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  10. 2026-10-09 20:06 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  11. 2026-10-08 17:11 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  12. 2026-10-07 23:47 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  13. 2026-10-06 15:17 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  14. 2026-10-05 17:42 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  15. 2026-10-04 23:21 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  16. 2026-10-03 14:25 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  17. 2026-10-01 19:49 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  18. 2026-10-01 16:13 UTCEG score recompute
  19. 2026-10-01 16:13 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  20. 2026-09-30 15:02 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  21. 2026-09-29 15:20 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  22. 2026-09-28 13:51 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  23. 2026-09-28 13:24 UTCEG score recompute
  24. 2026-09-28 13:24 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  25. 2026-09-27 13:47 UTCEPSS rescoreEPSS 2.2% · 81st percentile
Show 75 more
  1. 2026-09-26 15:58 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  2. 2026-09-24 11:52 UTCEG score recompute
  3. 2026-09-24 11:52 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  4. 2026-09-23 06:12 UTCEG score recompute
  5. 2026-09-23 06:12 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  6. 2026-09-18 19:27 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  7. 2026-09-18 05:45 UTCEG score recompute
  8. 2026-09-18 05:45 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  9. 2026-09-16 14:07 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  10. 2026-09-16 05:14 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  11. 2026-09-14 11:16 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  12. 2026-09-13 23:50 UTCEG score recompute
  13. 2026-09-13 23:50 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  14. 2026-09-13 16:46 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  15. 2026-09-13 08:26 UTCEG score recompute
  16. 2026-09-13 08:26 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  17. 2026-09-12 15:00 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  18. 2026-09-12 14:39 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  19. 2026-09-12 03:37 UTCEG score recompute
  20. 2026-09-12 03:37 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  21. 2026-09-11 14:52 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  22. 2026-09-11 09:36 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  23. 2026-09-10 09:34 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  24. 2026-09-08 22:00 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  25. 2026-09-07 16:01 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  26. 2026-09-06 14:04 UTCEG score recompute
  27. 2026-09-06 14:04 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  28. 2026-09-06 13:47 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  29. 2026-09-05 22:49 UTCEG score recompute
  30. 2026-09-05 22:49 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  31. 2026-09-04 05:06 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  32. 2026-09-02 14:11 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  33. 2026-09-01 13:53 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  34. 2026-09-01 04:39 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  35. 2026-08-30 19:17 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  36. 2026-08-30 18:40 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  37. 2026-08-30 07:37 UTCEG score recompute
  38. 2026-08-30 07:37 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  39. 2026-08-30 01:22 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  40. 2026-08-28 21:41 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  41. 2026-08-27 21:51 UTCEG score recompute
  42. 2026-08-27 21:51 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  43. 2026-08-27 14:25 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  44. 2026-08-27 01:32 UTCEG score recompute
  45. 2026-08-27 01:32 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  46. 2026-08-26 14:46 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  47. 2026-08-26 08:26 UTCEG score recompute
  48. 2026-08-26 08:26 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  49. 2026-08-25 13:48 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  50. 2026-08-25 10:14 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  51. 2026-08-24 21:44 UTCEG score recompute
  52. 2026-08-24 21:44 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  53. 2026-08-24 10:08 UTCEG score recompute
  54. 2026-08-24 10:08 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  55. 2026-08-23 23:05 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  56. 2026-08-23 11:39 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  57. 2026-08-23 00:37 UTCEG score recompute
  58. 2026-08-23 00:37 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  59. 2026-08-23 00:19 UTCEPSS rescoreEPSS 1.5% · 73rd percentile
  60. 2026-08-22 13:07 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  61. 2026-08-22 02:05 UTCEG score recompute
  62. 2026-08-22 02:05 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  63. 2026-08-21 23:49 UTCEPSS rescoreEPSS 1.5% · 73rd percentile
  64. 2026-08-21 15:02 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  65. 2026-08-21 04:00 UTCEG score recompute
  66. 2026-08-21 03:59 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  67. 2026-08-20 22:55 UTCEPSS rescoreEPSS 1.5% · 73rd percentile
  68. 2026-08-20 15:38 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  69. 2026-08-20 02:02 UTCEG score recompute
  70. 2026-08-20 02:02 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  71. 2026-08-19 17:03 UTCEPSS rescoreEPSS 1.5% · 72nd percentile
  72. 2026-08-19 09:32 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  73. 2026-08-18 22:28 UTCEG score recompute
  74. 2026-08-18 22:28 UTCGHSA enrichmentGHSA-6499-56p8-f7rq · GitHub severity LOW · GitHub CVSS 5.3
  75. 2026-08-18 13:48 UTCEPSS rescoreEPSS 1.5% · 72nd percentile

Related CVEs(same product + same CWE)

Frequently asked(5)

What is CVE-2026-15035?
CVE-2026-15035 is a high-severity vulnerability; its CVE record was published on July 8, 2026. A vulnerability was found in bentoml OpenLLM 0.6.30. This affects the function asyncruncommand of the file src/openllm/common.py of the component Model Repository Directory Name Handler. Performing a manipulation of the argument cmd results in command injection. Attacking locally is a requirement.…
When was the CVE record for CVE-2026-15035 published?
The CVE record for CVE-2026-15035 was published on July 8, 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 July 9, 2026; the record at its source may have been updated since.
Is CVE-2026-15035 actively exploited?
CVE-2026-15035 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 2.2% probability of exploitation in the next 30 days (82nd percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-15035?
CVE-2026-15035 has a CVSS v3 base score of 7.8 (NVD).
How do I remediate CVE-2026-15035?
A fix for CVE-2026-15035 is referenced (a reference tagged "Patch", often a source commit), but EchelonGraph has no release containing it on record. Check that reference and the vendor's advisory for a release that contains the fix and update to it; until then, restrict network exposure of the affected system or apply the vendor's mitigation. The vendor advisories EchelonGraph has for CVE-2026-15035 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-2026-15035

Explore →

Is Your Infrastructure Affected by CVE-2026-15035?

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

Book a Demo →Browse All CVEs