CVE-2023-43654TorchServe Server-Side Request Forgery
- 10.0CriticalCVSS base score
- 42.5%Exploitation in 30 daysEPSS · top 1.3% of all CVEs
- NoKnown exploitednot in CISA's KEV catalog
- 2Public exploitsMetasploit, Nuclei and Exploit-DB
Description
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.
Public exploit
An exploit or proof of concept is public: anyone can try it against an unpatched system. The public collections list a Metasploit module and a Nuclei template for it. CISA's SSVC rates its exploitation: a proof of concept is public.
Show the exploits2
Metasploit modules1 module
- PyTorch Model Server Registration and Deserialization RCE (Metasploit module) (opens in a new tab)
exploit/multi/http/torchserver_cve_2023_43654Rank excellentdisclosed 3 Oct 2023
Nuclei templates1 template
- PyTorch TorchServe SSRF (Nuclei template) (opens in a new tab)
http/cves/2023/CVE-2023-43654.yamlSeverity critical
Modules, templates and exploits as listed by the Metasploit Framework (BSD-3-Clause), ProjectDiscovery's Nuclei templates (MIT) and the Exploit Database (GPLv2), read once a day. Where the data comes from
Timeline
ID reserved
By GitHub_M
- 8 days later
· 8 days later
Published
- 17 months later
· 17 months later
Record updated
Changes after publication (a new score, a public exploit, EPSS crossing 1, 10 or 50 %, leaving KEV) are kept since November 2026; earlier ones are not known.
Scores
| Scored by | CVSS | Score | Vector |
|---|---|---|---|
| GitHub_MCNA (assigner) | 3.1 | Critical10.0 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H |
| NVDNVD · Modified | 3.1 | Critical9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
- EPSS (exploitation in 30 days)
- 42.5% · top 1.3% of all CVEs (17 Nov 2026)
- CISA SSVC
- Exploitation: poc · Automatable: yes · Technical impact: total
The list uses the assigner's score when there is one, then CISA's, then NVD's: Critical 10.0.
Affected products
Affected packages
From reviewed advisories of the GitHub Advisory Database.
- PyPItorchserveGHSA-8fxr-qfr9-p34w (opens in a new tab)
References
References4
- https://github.com/pytorch/serve/security/advisories/GHSA-8fxr-qfr9-p34w (opens in a new tab)x_refsource_CONFIRMx_transferred
- https://github.com/pytorch/serve/pull/2534 (opens in a new tab)x_refsource_MISCx_transferred
- https://github.com/pytorch/serve/releases/tag/v0.8.2 (opens in a new tab)x_refsource_MISCx_transferred
- http://packetstormsecurity.com/files/175095/PyTorch-Model-Server-Registration-Deserialization-Remote-Code-Execution.html (opens in a new tab)x_transferred
Sources
The same CVE in the primary databases and aggregators, to check against.
- CVE.org record (opens in a new tab)
- CVE List JSON (GitHub) (opens in a new tab)
- NVD (opens in a new tab)
- FIRST EPSS (opens in a new tab)
- EUVD EUVD-2023-2697 (opens in a new tab)
- OSV.dev (opens in a new tab)
- GitHub Advisory GHSA-8fxr-qfr9-p34w (opens in a new tab)
- CIRCL Vulnerability-Lookup (opens in a new tab)
Badge for a README or a ticket
[](https://cveledger.app/cve/CVE-2023-43654)Record last updated .