CVE-2024-35198: TorchServe vulnerable to bypass of allowed_urls configuration

Should you act?

Critical and remotely reachable

No known exploitation yet, but it is network-reachable without credentials. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.

• No confirmed exploitation. It is not in CISA’s KEV catalog and CISA’s SSVC assessment records no known exploitation. That can change quickly after a public write-up; re-check if you are affected.
• EPSS 0.8%, percentile 56: FIRST’s model estimates a 0.8% chance of exploitation activity in the next 30 days, higher than 56% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
• Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
• Only applies if your dependency tree includes torchserve (PyPI) < 0.11.0, fixed in 0.11.0. Check your lockfile, including transitive dependencies.

What it is

TorchServe is a flexible and easy-to-use tool for serving and scaling PyTorch models in production. TorchServe 's check on allowedurls configuration can be by-passed if the URL contains characters such as ".." but it does not prevent the model from being downloaded into the model store. Once a file is downloaded, it can be referenced without providing a URL the second time, which effectively bypasses the allowedurls security check. Customers using PyTorch inference Deep Learning Containers (DLC) through Amazon SageMaker and EKS are not affected. This issue in TorchServe has been fixed by validating the URL without characters such as ".." before downloading see PR #3082. TorchServe release 0.11.0 includes the fix to address this vulnerability. Users are advised to upgrade. There are no known workarounds for this vulnerability.

From the GitHub advisory

Impact TorchServe's check on allowedurls configuration can be by-passed if the URL contains characters such as ".." but it does not prevent the model from being downloaded into the model store. Once a file is downloaded, it can be referenced without providing a URL the second time, which effectively bypasses the allowedurls security check. Customers using PyTorch inference Deep Learning Containers (DLC) through Amazon SageMaker and EKS are not affected.

Patches This issue in TorchServe has been fixed by validating the URL without characters such as ".." before downloading: #3082.

TorchServe release 0.11.0 includes the fix to address this vulnerability.

References #3082 TorchServe release v0.11.0

Thank Kroll Cyber Risk for for responsibly disclosing this issue.

Weakness type: CWE-706, CWE-22.

Product: torchserve (PyPI) · Assigned by: GitHub_M · Published: 2024-07-18

Affected and fixed versions

Severity scores

• Attack vector: network (remotely reachable)
• Attack complexity: low
• Attack requirements: none
• Privileges required: none (no login)
• User interaction: none

CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.

Exploitation and urgency

• CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
• CISA SSVC assessment: exploitation none, automatable no, technical impact partial.
• FIRST EPSS (model of 2026-10-21): 0.80% probability of exploitation activity in the next 30 days; percentile 56.

Timeline

• 2024-07-18 — CVE record published by GitHub_M
• 2024-07-18 — GitHub-reviewed advisory GHSA-wxcx-gg9c-fwp2 published (critical)
• 2024-08-07 — CVE record last updated

Sources and references

Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.

Vulnerability records

1. GitHub Advisory GHSA-wxcx-gg9c-fwp2 github.com
2. CVE.org record CVE-2024-35198 cve.org
3. NVD entry CVE-2024-35198 nvd.nist.gov

Other references from the CVE record and advisory

1. github.com github.com
2. github.com github.com
3. github.com github.com
4. github.com github.com

Critical PyPI advisories · Today’s Security Digest