CVE-2025-29770
Last modified
CVE-2025-29770 is a medium-severity vulnerability rated 6.5/10 on the CVSS scale. vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. The outlines library is one of the backends used by vLLM to support structured output (a.k.a. EPSS estimates a 0.42% chance of exploitation in the next 30 days.
Description
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. The outlines library is one of the backends used by vLLM to support structured output (a.k.a. guided decoding). Outlines provides an optional cache for its compiled grammars on the local filesystem. This cache has been on by default in vLLM. Outlines is also available by default through the OpenAI compatible API server. The affected code in vLLM is vllm/model_executor/guided_decoding/outlines_logits_processors.py, which unconditionally uses the cache from outlines. A malicious user can send a stream of very short decoding requests with unique schemas, resulting in an addition to the cache for each request. This can result in a Denial of Service if the filesystem runs out of space. Note that even if vLLM was configured to use a different backend by default, it is still possible to choose outlines on a per-request basis using the guided_decoding_backend key of the extra_body field of the request. This issue applies only to the V0 engine and is fixed in 0.8.0.
Metrics
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Weakness Enumeration
Affected Software
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | < 0.8.0 |
References
- https://github.com/vllm-project/vllm/pull/14837Issue Tracking, Patch
- https://github.com/vllm-project/vllm/security/advisories/GHSA-mgrm-fgjv-mhv8Patch, Vendor Advisory
Timeline
- Published
- Last Modified
- Status
- Analyzed
Frequently Asked Questions
What is CVE-2025-29770?
How severe is CVE-2025-29770?
How do I fix CVE-2025-29770?
How Strix Helps
- How Strix found a critical auth bypass in etcdStrix autonomously discovered a critical authentication bypass in etcd, later designated CVE-2026-33413.
- Autonomous PentestingAI agents that find and validate exploitable vulnerabilities like this one across your applications.
- PR ReviewsPentest every pull request so vulnerable code is caught before it ships to production.
- AI Penetration TestingHow AI-driven penetration testing continuously covers your attack surface.
Related CVEs from 2025
- CVE-2025-2976A vulnerability was found in GFI KerioConnect 10.0.6. It has…5.4
- CVE-2025-29763Rejected reason: “This CVE ID is Rejected and will not be us…
- CVE-2025-29766Tuleap is an Open Source Suite to improve management of soft…4.3
- CVE-2025-29768Vim, a text editor, is vulnerable to potential data loss wit…4.4
- CVE-2025-29769libvips is a demand-driven, horizontally threaded image proc…5.5
- CVE-2025-2977A vulnerability was found in GFI KerioConnect 10.0.6. It has…5.4
- CVE-2025-29771HtmlSanitizer is a client-side HTML Sanitizer. Versions prio…5.3
- CVE-2025-29772OpenEMR is a free and open source electronic health records …6.1
- CVE-2025-29773Froxlor is open-source server administration software. A vul…7.8
- CVE-2025-29774xml-crypto is an XML digital signature and encryption librar…9.3
- CVE-2025-29775xml-crypto is an XML digital signature and encryption librar…9.3
- CVE-2025-29776Azle is a WebAssembly runtime for TypeScript and JavaScript …8.7
Are you affected by CVE-2025-29770?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST
