GHSA-HF3C-WXG2-49Q9
Vulnerability from github – Published: 2025-04-15 21:21 – Updated: 2025-04-15 21:21Impact
This report is to highlight a vulnerability in XGrammar, a library used by the structured output feature in vLLM. The XGrammar advisory is here: https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3
The xgrammar library is the default backend used by vLLM to support structured output (a.k.a. guided decoding). Xgrammar provides a required, built-in cache for its compiled grammars stored in RAM. xgrammar is available by default through the OpenAI compatible API server with both the V0 and V1 engines.
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 by consuming all of the system's RAM.
Note that even if vLLM was configured to use a different backend by default, it is still possible to choose xgrammar on a per-request basis using the guided_decoding_backend key of the extra_body field of the request with the V0 engine. This per-request choice is not available when using the V1 engine.
Patches
- https://github.com/vllm-project/vllm/pull/16283
Workarounds
There is no way to workaround this issue in existing versions of vLLM other than preventing untrusted access to the OpenAI compatible API server.
References
- https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3
{
"affected": [
{
"package": {
"ecosystem": "PyPI",
"name": "vllm"
},
"ranges": [
{
"events": [
{
"introduced": "0.6.5"
},
{
"fixed": "0.8.4"
}
],
"type": "ECOSYSTEM"
}
]
}
],
"aliases": [],
"database_specific": {
"cwe_ids": [
"CWE-1395",
"CWE-770"
],
"github_reviewed": true,
"github_reviewed_at": "2025-04-15T21:21:04Z",
"nvd_published_at": null,
"severity": "MODERATE"
},
"details": "### Impact\n\nThis report is to highlight a vulnerability in XGrammar, a library used by the structured output feature in vLLM. The XGrammar advisory is here: https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3\n\nThe [xgrammar](https://xgrammar.mlc.ai/docs/) library is the default backend used by vLLM to support structured output (a.k.a. guided decoding). Xgrammar provides a required, built-in cache for its compiled grammars stored in RAM. xgrammar is available by default through the OpenAI compatible API server with both the V0 and V1 engines.\n\nA 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 by consuming all of the system\u0027s RAM.\n\nNote that even if vLLM was configured to use a different backend by default, it is still possible to choose xgrammar on a per-request basis using the `guided_decoding_backend` key of the `extra_body` field of the request with the V0 engine. This per-request choice is not available when using the V1 engine. \n### Patches\n\n* https://github.com/vllm-project/vllm/pull/16283\n\n### Workarounds\n\nThere is no way to workaround this issue in existing versions of vLLM other than preventing untrusted access to the OpenAI compatible API server.\n\n### References\n\n* https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3",
"id": "GHSA-hf3c-wxg2-49q9",
"modified": "2025-04-15T21:21:04Z",
"published": "2025-04-15T21:21:04Z",
"references": [
{
"type": "WEB",
"url": "https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3"
},
{
"type": "WEB",
"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-hf3c-wxg2-49q9"
},
{
"type": "WEB",
"url": "https://github.com/vllm-project/vllm/pull/16283"
},
{
"type": "WEB",
"url": "https://github.com/vllm-project/vllm/commit/cb84e45ac75b42ba6795145923e8eb323bb825ad"
},
{
"type": "PACKAGE",
"url": "https://github.com/vllm-project/vllm"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
"type": "CVSS_V3"
}
],
"summary": "vLLM vulnerable to Denial of Service by abusing xgrammar cache"
}
Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Vulnerability timeline
Sightings and recorded dates, grouped by day · UTC
How durations are calculated
Following the VTEM framework (Black Hat USA 2015), time to patch starts when the vendor or a coordinator was informed, total time to patch at discovery, and disclosure to patch at public disclosure; vendor response time runs from the report to its acknowledgement. Time to exploit and time unpatched start at the earliest discovery or report, falling back to public disclosure. Unpatched time ends at the first recorded patch, or the calculation time when no patch is recorded. Exploitation to patch shows the interval between those two events; a published proof of concept is a public exploit, not exploitation.
Each result shows its source dates. A negative interval means the end event came first; when date-only inputs leave the order open, the result says so. Date-only inputs are approximate. The earliest evidence wins: KEV report dates and sightings are labelled as such. Records describing another vulnerability are listed but never calculated from, and a PoC alone does not establish exploitation. Missing patch evidence does not prove that no patch exists. Filters below change the event list only.
Loading timeline…
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.