CVE-2023-43654

CRITICALNVD 9.89.8
EchelonGraph scoreMEDIUM confidence

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

Score 9.8 from GitHub Security Advisory (severity: CRITICAL) published 2023-10-02. NVD baseline CVSS 9.8; sources differ by 0.0.

Triggered by: GitHub Security Advisory CVSS
Sources: EPSS, GitHub Security Advisory, NVD CVSS v3
Weaponized

Also known asEUVD-2023-2697 (ENISA EUVD) · GHSA-8fxr-qfr9-p34w (GitHub Security Advisories) · PYSEC-2026-553 (OSV.dev)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).
  • Public exploit code is available (Metasploit, other public proof-of-concept code)
CISA-KEV: Not listedEPSS PROB: 42%CVSS: 9.8Exploit: Metasploit · other public PoCExposed services: Not assessed

A fix is available — apply it.

TorchServe is a tool for serving and scaling PyTorch models in production. TorchServe default configuration lacks proper input validation, enabling third parties to invoke remote HTTP download requests and write files to the disk. This issue could be taken advantage of to compromise the integrity of the system and sensitive data. This issue is present in versions 0.1.0 to 0.8.1. A user is able to load the model of their choice from any URL that they would like to use. The user of TorchServe is responsible for configuring both the allowed_urls and specifying the model URL to be used. A pull request to warn the user when the default value for allowed_urls is used has been merged in PR #2534. TorchServe release 0.8.2 includes this change. Users are advised to upgrade. There are no known workarounds for this issue.

CVSS v3
9.8
EG Score
9.8CRITICALmedium confidence
EG Risk
85
EG Risk 85/100

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.
Exploitation65% × 40%
EchelonGraph's fixed weight for EG-KEV Tier 2 (Weaponized): 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, Track* at medium and Attend at high mission impact.
Exploitation public PoC (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
42%
EPSS %ILE
98th
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
42% within 30 daysSource: FIRST EPSS (model v2026.06.15, score date 2026-11-12). 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: 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, 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 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 28, 2023

Last Modified

June 17, 2026

Advisory Details (4)

Auto-updated Oct 17, 2026
Patch available. Sources: github, github_pr, github_release.
GitHub advisoryMentions a patch (unverified)

TorchServe SSRF · Advisory · pytorch/serve · GitHub

https://github.com/pytorch/serve/security/advisories/GHSA-8fxr-qfr9-p34w
GitHub release Patch Available

TorchServe v0.8.2 Release Notes

Patch available: pytorch/serve v0.8.2

https://github.com/pytorch/serve/releases/tag/v0.8.2
GitHub pull request

Issue warning about allowed_urls when default value is used

Fix merged in pytorch/serve PR #2534 on 2023-08-22 — awaiting tagged release

https://github.com/pytorch/serve/pull/2534
Web page

Packet Storm

http://packetstormsecurity.com/files/175095/PyTorch-Model-Server-Registration-Deserialization-Remote-Code-Execution.html

Vendor Advisories for CVE-2023-43654(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
piptorchserve @ 0.8.2 (fixes >= 0.1.0, < 0.8.2)—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
torchserve0.1.1 ... 0.8.1 (18 versions)
  • 0.1.0 up to 0.8.2: fixed in 0.8.2
—

Weakness Classification(1)

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

Data Freshness Timeline

(refreshed 13× in last 7d / 41× 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 its CVE.org record (CNA or CISA ADP). 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). "EchelonGraph re-scored" is our own recompute of this CVE's score, not an update from a source, and is not counted in the refreshes above. Most recent first.

Showing the most recent 100 of 221 rows on record for this CVE, as 96 entries (4 repeats merged).

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. 4 repeat rows among the latest 100 are merged into the row they repeat. The 121 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-11-13 16:45 UTCEPSS rescoreEPSS 42% · 98th percentile
  2. 2026-11-12 20:38 UTCEchelonGraph re-scored
  3. 2026-11-12 20:38 UTCGHSA enrichmentGHSA-8fxr-qfr9-p34w · GitHub severity CRITICAL · GitHub CVSS 9.8
  4. 2026-11-12 16:30 UTCEPSS rescoreEPSS 42% · 98th percentile
  5. 2026-11-11 20:00 UTCEchelonGraph re-scored
  6. 2026-11-11 20:00 UTCGHSA enrichmentGHSA-8fxr-qfr9-p34w · GitHub severity CRITICAL · GitHub CVSS 9.8
  7. 2026-11-11 16:33 UTCEPSS rescoreEPSS 42% · 98th percentile
  8. 2026-11-10 19:23 UTCEchelonGraph re-scored
  9. 2026-11-10 19:23 UTCGHSA enrichmentGHSA-8fxr-qfr9-p34w · GitHub severity CRITICAL · GitHub CVSS 9.8
  10. 2026-11-10 16:37 UTCEPSS rescoreEPSS 42% · 98th percentile
  11. 2026-11-09 18:41 UTCEchelonGraph re-scored
  12. 2026-11-09 18:41 UTCGHSA enrichmentGHSA-8fxr-qfr9-p34w · GitHub severity CRITICAL · GitHub CVSS 9.8
  13. 2026-11-09 16:30 UTCEPSS rescoreEPSS 42% · 98th percentile
  14. 2026-11-08 18:04 UTCEchelonGraph re-scored
  15. 2026-11-08 18:04 UTCGHSA enrichmentGHSA-8fxr-qfr9-p34w · GitHub severity CRITICAL · GitHub CVSS 9.8
  16. 2026-11-08 16:35 UTCEPSS rescoreEPSS 42% · 98th percentile
  17. 2026-11-07 17:27 UTCEchelonGraph re-scored
  18. 2026-11-07 17:27 UTCGHSA enrichmentGHSA-8fxr-qfr9-p34w · GitHub severity CRITICAL · GitHub CVSS 9.8
  19. 2026-11-07 16:35 UTCEPSS rescoreEPSS 42% · 98th percentile
  20. 2026-11-06 16:49 UTCEchelonGraph re-scored
  21. 2026-11-06 16:49 UTCGHSA enrichmentGHSA-8fxr-qfr9-p34w · GitHub severity CRITICAL · GitHub CVSS 9.8
  22. 2026-11-06 16:31 UTCEPSS rescoreEPSS 42% · 98th percentile
  23. 2026-11-05 16:33 UTCEPSS rescoreEPSS 42% · 98th percentile
  24. 2026-11-05 16:11 UTCEchelonGraph re-scored
  25. 2026-11-05 16:11 UTCGHSA enrichmentGHSA-8fxr-qfr9-p34w · GitHub severity CRITICAL · GitHub CVSS 9.8
Show 71 more
  1. 2026-11-04 16:31 UTCEPSS rescoreEPSS 42% · 98th percentile
  2. 2026-11-04 16:25 UTCOSV refresh
  3. 2026-11-04 15:29 UTCEchelonGraph re-scored
  4. 2026-11-04 15:29 UTCGHSA enrichmentGHSA-8fxr-qfr9-p34w · GitHub severity CRITICAL · GitHub CVSS 9.8
  5. 2026-11-03 16:41 UTCEPSS rescoreEPSS 42% · 98th percentile
  6. 2026-11-03 14:50 UTCEchelonGraph re-scored
  7. 2026-11-03 14:50 UTCGHSA enrichmentGHSA-8fxr-qfr9-p34w · GitHub severity CRITICAL · GitHub CVSS 9.8
  8. 2026-11-02 14:01 UTCEchelonGraph re-scored
  9. 2026-11-02 14:01 UTCGHSA enrichmentGHSA-8fxr-qfr9-p34w · GitHub severity CRITICAL · GitHub CVSS 9.8
  10. 2026-11-01 16:31 UTCEPSS rescoreEPSS 42% · 98th percentile
  11. 2026-11-01 13:23 UTCGHSA enrichmentGHSA-8fxr-qfr9-p34w · GitHub severity CRITICAL · GitHub CVSS 9.8
  12. 2026-11-01 08:19 UTCGHSA enrichmentGHSA-8fxr-qfr9-p34w · GitHub severity CRITICAL · GitHub CVSS 9.8
  13. 2026-11-01 08:19 UTCEchelonGraph re-scored
  14. 2026-10-31 16:30 UTCEPSS rescoreEPSS 42% · 98th percentile
  15. 2026-10-31 12:45 UTCEchelonGraph re-scored
  16. 2026-10-30 16:31 UTCEPSS rescoreEPSS 42% · 98th percentile
  17. 2026-10-30 12:08 UTCEchelonGraph re-scored
  18. 2026-10-29 16:30 UTCEPSS rescoreEPSS 42% · 98th percentile
  19. 2026-10-29 11:30 UTCEchelonGraph re-scored
  20. 2026-10-28 16:29 UTCEPSS rescoreEPSS 42% · 98th percentile
  21. 2026-10-28 10:53 UTCEchelonGraph re-scored
  22. 2026-10-27 16:29 UTCEPSS rescoreEPSS 42% · 98th percentile
  23. 2026-10-27 09:21 UTCEchelonGraph re-scored
  24. 2026-10-25 17:34 UTCEchelonGraph re-scored
  25. 2026-10-25 16:29 UTCEPSS rescoreEPSS 42% · 98th percentile
  26. 2026-10-25 07:43 UTCEchelonGraph re-scored
  27. 2026-10-24 16:29 UTCEPSS rescoreEPSS 42% · 98th percentile
  28. 2026-10-24 07:05 UTCEchelonGraph re-scored
  29. 2026-10-23 16:29 UTCEPSS rescoreEPSS 42% · 98th percentile
  30. 2026-10-23 06:25 UTCEchelonGraph re-scored
  31. 2026-10-22 16:31 UTCEPSS rescoreEPSS 42% · 98th percentile
  32. 2026-10-22 05:47 UTCEchelonGraph re-scored
  33. 2026-10-21 16:29 UTCEPSS rescoreEPSS 42% · 98th percentile
  34. 2026-10-21 05:06 UTCEchelonGraph re-scored
  35. 2026-10-20 16:30 UTCEPSS rescoreEPSS 42% · 98th percentile
  36. 2026-10-20 04:28 UTCEchelonGraph re-scored
  37. 2026-10-19 16:29 UTCEPSS rescoreEPSS 42% · 98th percentile
  38. 2026-10-19 03:50 UTCEchelonGraph re-scored
  39. 2026-10-18 03:12 UTCEchelonGraph re-scored
  40. 2026-10-17 16:30 UTCEPSS rescoreEPSS 42% · 98th percentile
  41. 2026-10-17 02:34 UTCEchelonGraph re-scored
  42. 2026-10-16 16:36 UTCEPSS rescoreEPSS 42% · 98th percentile
  43. 2026-10-16 01:55 UTCEchelonGraph re-scored
  44. 2026-10-15 16:29 UTCEPSS rescoreEPSS 42% · 98th percentile
  45. 2026-10-14 21:23 UTCEchelonGraph re-scored
  46. 2026-10-14 16:30 UTCEPSS rescoreEPSS 42% · 98th percentile
  47. 2026-10-13 17:24 UTCEchelonGraph re-scored
  48. 2026-10-13 16:30 UTCEPSS rescoreEPSS 42% · 98th percentile
  49. 2026-10-12 16:44 UTCEchelonGraph re-scored
  50. 2026-10-11 21:45 UTCEchelonGraph re-scored
  51. 2026-10-11 13:45 UTCEPSS rescoreEPSS 42% · 98th percentile
  52. 2026-10-09 20:05 UTCEPSS rescoreEPSS 42% · 98th percentile
  53. 2026-10-08 17:06 UTCEPSS rescoreEPSS 42% · 98th percentile
  54. 2026-10-07 23:46 UTCEPSS rescoreEPSS 42% · 98th percentile
  55. 2026-10-06 15:15 UTCEPSS rescoreEPSS 44% · 98th percentile
  56. 2026-10-03 14:23 UTCEPSS rescoreEPSS 42% · 98th percentile
  57. 2026-10-01 19:48 UTCEPSS rescoreEPSS 41% · 98th percentile
  58. 2026-09-30 16:31 UTCEchelonGraph re-scored
  59. 2026-09-30 15:01 UTCEPSS rescoreEPSS 41% · 98th percentile
  60. 2026-09-29 15:17 UTCEPSS rescoreEPSS 40% · 98th percentile
  61. 2026-09-27 13:42 UTCEPSS rescoreEPSS 36% · 98th percentile
  62. 2026-09-26 15:56 UTCEPSS rescoreEPSS 36% · 98th percentile
  63. 2026-09-26 00:22 UTCEPSS rescoreEPSS 36% · 98th percentile
  64. 2026-09-24 14:01 UTCEPSS rescoreEPSS 36% · 98th percentile
  65. 2026-09-23 13:46 UTCEPSS rescoreEPSS 36% · 98th percentile
  66. 2026-09-22 22:01 UTCOSV refresh
  67. 2026-09-18 19:25 UTCEPSS rescoreEPSS 36% · 98th percentile
  68. 2026-09-17 19:25 UTCEPSS rescoreEPSS 36% · 98th percentile
  69. 2026-09-16 14:06 UTCEPSS rescoreEPSS 36% · 98th percentile
  70. 2026-09-16 05:11 UTCEPSS rescoreEPSS 36% · 98th percentile
  71. 2026-09-12 14:58 UTCEPSS rescoreEPSS 36% · 98th percentile

Publicly available exploits

(4 references)

Public exploit code is referenced for this CVE (1 Metasploit module, 1 GitHub PoC), as are 1 Nuclei detection template, 1 GitHub checker repository. A detection template checks whether a system is affected; it is not necessarily exploit code. A GitHub repository named or described as a checker or scanner checks whether a system is affected; it is not necessarily exploit code. Defenders should treat patch urgency accordingly.

  • Metasploitexploit/multi/http/torchserver_cve_2023_43654✓ verified
    Published Oct 12, 2023

    PyTorch Model Server Registration and Deserialization RCE

    Open source ↗
  • Nucleihttp/cves/2023/CVE-2023-43654.yaml
    Published Sep 19, 2024

    PyTorch TorchServe SSRF

    Open source ↗
  • GitHub PoCOligoCyberSecurity/CVE-2023-43654
    Published May 28, 2024

    Demo for CVE-2023-43654 - Remote Code Execution in PyTorch TorchServe

    Open source ↗
  • GitHub checkerOligoCyberSecurity/ShellTorchChecker
    Published Oct 2, 2023

    A tool that checks if a TorchServe instance is vulnerable to CVE-2023-43654

    Open source ↗

Related CVEs(same product + same CWE)

Frequently asked(5)

What is CVE-2023-43654?
CVE-2023-43654 is a critical-severity vulnerability; its CVE record was published on September 28, 2023. TorchServe is a tool for serving and scaling PyTorch models in production. TorchServe default configuration lacks proper input validation, enabling third parties to invoke remote HTTP download requests and write files to the disk. This issue could be taken advantage of to compromise the integrity…
When was the CVE record for CVE-2023-43654 published?
The CVE record for CVE-2023-43654 was published on September 28, 2023. 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 June 17, 2026; the record at its source may have been updated since.
Is CVE-2023-43654 actively exploited?
CVE-2023-43654 is not currently on CISA's Known Exploited Vulnerabilities catalog. EchelonGraph's EG-KEV model places it in Tier 2 (Weaponized), which is not evidence of exploitation: a Metasploit module exists for it. EchelonGraph does not test whether exploit code works. FIRST EPSS estimates a 42% probability of exploitation in the next 30 days (98th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2023-43654?
CVE-2023-43654 has a CVSS v3 base score of 9.8 (NVD).
How do I remediate CVE-2023-43654?
A fix for CVE-2023-43654 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2023-43654 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-2023-43654

Explore →

Is Your Infrastructure Affected by CVE-2023-43654?

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

Book a Demo →Browse All CVEs