TorchServe gRPC Port Exposure

Description

Impact

The two gRPC ports 7070 and 7071, are not bound to localhost by default, so when TorchServe is launched, these two interfaces are bound to all interfaces. Customers using PyTorch inference Deep Learning Containers (DLC) through Amazon SageMaker and EKS are not affected.

Patches

This issue in TorchServe has been fixed in #3083.

TorchServe release 0.11.0 includes the fix to address this vulnerability.

References

Thank Kroll Cyber Risk for for responsibly disclosing this issue.

If you have any questions or comments about this advisory, we ask that you contact AWS Security via our vulnerability reporting page or directly via email to [email protected]. Please do not create a public GitHub issue.

Basic information

Type
reviewed
Severity
high
Advisory on GitHub
Open advisory ↗
Repository advisory
Open repository advisory ↗
Source code
Browse source ↗
Published (advisory)
2024-07-18 22:06:41 UTC
Updated
2024-08-07 16:06:00 UTC
GitHub reviewed
2024-07-18 22:06:41 UTC
NVD published
2024-07-18

EPSS Score

Score Percentile
0.07% 20.99%

CVSS Scores

Base score Version Severity Vector
8.2 3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:H Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:N)
No account or special rights needed—anonymous or random user is enough.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:L)
Some sensitive info could get out, but not a total data dump.
Integrity (I:N)
Data isn’t meaningfully altered or forged.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
8.8 4.0
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:N/VA:H/SC:N/SI:N/SA:N Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network.
Attack complexity (AC:L)
Exploitation conditions are straightforward and stable.
Attack requirements (AT:N)
No additional preconditions are required beyond normal reachability.
Privileges required (PR:N)
No privileges are required.
User interaction (UI:N)
No user interaction is required.
Vulnerable system confidentiality impact (VC:L)
Limited confidentiality impact on the vulnerable system.
Vulnerable system integrity impact (VI:N)
No integrity impact on the vulnerable system.
Vulnerable system availability impact (VA:H)
High availability impact on the vulnerable system.
Subsequent system confidentiality impact (SC:N)
No confidentiality impact on subsequent systems.
Subsequent system integrity impact (SI:N)
No integrity impact on subsequent systems.
Subsequent system availability impact (SA:N)
No availability impact on subsequent systems.

Identifiers

CWEs

CWE id Name
CWE-668 Exposure of Resource to Wrong Sphere
CWE-1256 Improper Restriction of Software Interfaces to Hardware Features

Affected packages (1)

Vulnerable version ranges and first patched releases as published by GitHub.

Ecosystem Package Vulnerable range First patched Vulnerable functions
pip torchserve >= 0.3.0, < 0.11.0 0.11.0

References

cvelogic Threat Intelligence