In all versions of PyTorch's TorchServe, a predictable extraction directory in /tmp lets a local user swap the model
Source GCVE Database
Not known to be exploited · CVSS 7.8 High.
Data as of 6 Nov 2026, 22:42 UTC
Thin evidence
One scorer or none| CNA (Akrites) | CVSS 3.1 | 7.8 |
|---|
CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:HExploitation evidence
Disclosed: evidence found.
CVE published 6 Nov 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 6 Nov 2026.
What to do
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| PyTorchTorchServe | Affected
| Fixed in– |
GitHubTorchServepkg:github/TorchServeOther threats | Affected
| Fixed in– |
Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.
AI-suggested
Until a fix is available, restrict local user access to systems running TorchServe and monitor for suspicious activity related to /tmp directory usage. Avoid running TorchServe with unnecessary elevated privileges.
Description
A vulnerability in all versions of PyTorch's TorchServe allows a local user to exploit a predictable extraction directory in /tmp. This flaw enables the attacker to swap the model handler and execute code with the privileges of the TorchServe service account, resulting in local privilege escalation.