CVE-2026-0599 in the critical feed json
Unbounded External Image Fetch in Validation Leads to Resource-Exhaustion DoS in huggingface/text-generation-inference
published 9mo ago modified 4mo ago also GHSA-j7x9-7j54-2v3h , PYSEC-2026-1965 , EUVD-2026-5137
- cvss
- 7.5
- version 3.0, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 29.5%
- EPSS 29.5% chance of exploitation in 30 days, percentile 98%
- public exploits
- 0
- none known
Summary
A vulnerability in huggingface/text-generation-inference version 3.3.6 allows unauthenticated remote attackers to exploit unbounded external image fetching during input validation in VLM mode. The issue arises when the router scans inputs for Markdown image links and performs a blocking HTTP GET request, reading the entire response body into memory and cloning it before decoding. This behavior can lead to resource exhaustion, including network bandwidth saturation, memory inflation, and CPU overutilization. The vulnerability is triggered even if the request is later rejected for exceeding token limits. The default deployment configuration, which lacks memory usage limits and authentication, exacerbates the impact, potentially crashing the host machine. The issue is resolved in version 3.3.7.
Patch / fix
- pypi text-generation 3.3.7
- huggingface huggingface/text-generation-inference 3.3.7
Is CVE-2026-0599 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.
Check with FencerCISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- yes
- Technical impact
- partial
- Assessed
- 9mo ago
Exploit prediction
29.49% chance of exploitation in the next 30 days, higher than 98% of all scored CVEs (FIRST EPSS, 2026-11-09).
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.0 | 7.5 | CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H |
| OSV | 3.0 | 7.5 | CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H |
| GitHub | 3.0 | 7.5 | CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | text-generation | <3.3.7 |
3.3.7 |
Affected products
- huggingface huggingface/text-generation-inference
Classification
- Weakness
-
- CWE-400 Uncontrolled Resource Consumption
References
-
github.com
/huggingface/text-generation-inference/commit/24ee40d143d8d046039f12f76940a85886cbe152
web
-
huntr.com
/bounties/1d3f2085-666c-4441-b265-22f6f7d8d9cd
web
-
nvd.nist.gov
/vuln/detail/CVE-2026-0599
advisory
-
github.com
/huggingface/text-generation-inference
package
-
pypi.org
/project/text-generation
package
-
github.com
/advisories/GHSA-j7x9-7j54-2v3h
advisory
Sources
- CVE List CVE-2026-0599
- GitHub Advisory GHSA-j7x9-7j54-2v3h
- NVD CVE-2026-0599
- OSV PYSEC-2026-1965
Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.