pysec - pysec-2025-62

PYSEC-2025-62

Vulnerability from pysec - Published: 2025-02-07 20:15 - Updated: 2025-07-01 23:22

Details

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. Prefix caching makes use of Python's built-in hash() function. As of Python 3.12, the behavior of hash(None) has changed to be a predictable constant value. This makes it more feasible that someone could try exploit hash collisions. The impact of a collision would be using cache that was generated using different content. Given knowledge of prompts in use and predictable hashing behavior, someone could intentionally populate the cache using a prompt known to collide with another prompt in use. This issue has been addressed in version 0.7.2 and all users are advised to upgrade. There are no known workarounds for this vulnerability.

Impacted products

Name	purl
vllm	pkg:pypi/vllm

Aliases

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "vllm",
        "purl": "pkg:pypi/vllm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "432117cd1f59c76d97da2eaff55a7d758301dbc7"
            }
          ],
          "repo": "https://github.com/python/cpython",
          "type": "GIT"
        },
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.7.2"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ],
      "versions": [
        "0.0.1",
        "0.1.0",
        "0.1.1",
        "0.1.2",
        "0.1.3",
        "0.1.4",
        "0.1.5",
        "0.1.6",
        "0.1.7",
        "0.2.0",
        "0.2.1",
        "0.2.1.post1",
        "0.2.2",
        "0.2.3",
        "0.2.4",
        "0.2.5",
        "0.2.6",
        "0.2.7",
        "0.3.0",
        "0.3.1",
        "0.3.2",
        "0.3.3",
        "0.4.0",
        "0.4.0.post1",
        "0.4.1",
        "0.4.2",
        "0.4.3",
        "0.5.0",
        "0.5.0.post1",
        "0.5.1",
        "0.5.2",
        "0.5.3",
        "0.5.3.post1",
        "0.5.4",
        "0.5.5",
        "0.6.0",
        "0.6.1",
        "0.6.1.post1",
        "0.6.1.post2",
        "0.6.2",
        "0.6.3",
        "0.6.3.post1",
        "0.6.4",
        "0.6.4.post1",
        "0.6.5",
        "0.6.6",
        "0.6.6.post1",
        "0.7.0",
        "0.7.1"
      ]
    }
  ],
  "aliases": [
    "CVE-2025-25183",
    "GHSA-rm76-4mrf-v9r8"
  ],
  "details": "vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. Prefix caching makes use of Python\u0027s built-in hash() function. As of Python 3.12, the behavior of hash(None) has changed to be a predictable constant value. This makes it more feasible that someone could try exploit hash collisions. The impact of a collision would be using cache that was generated using different content. Given knowledge of prompts in use and predictable hashing behavior, someone could intentionally populate the cache using a prompt known to collide with another prompt in use. This issue has been addressed in version 0.7.2 and all users are advised to upgrade. There are no known workarounds for this vulnerability.",
  "id": "PYSEC-2025-62",
  "modified": "2025-07-01T23:22:49.083695+00:00",
  "published": "2025-02-07T20:15:34+00:00",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-rm76-4mrf-v9r8"
    },
    {
      "type": "FIX",
      "url": "https://github.com/python/cpython/commit/432117cd1f59c76d97da2eaff55a7d758301dbc7"
    },
    {
      "type": "REPORT",
      "url": "https://github.com/vllm-project/vllm/pull/12621"
    }
  ]
}

CVE-2025-25183 (GCVE-0-2025-25183)

Vulnerability from cvelistv5 – Published: 2025-02-07 19:59 – Updated: 2025-02-12 20:51

Summary

Severity ?

2.6 (Low)


                        
                          CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:N/I:L/A:N

CWE

CWE-354 - Improper Validation of Integrity Check Value

Assigner

GitHub_M

References

URL

Tags

	https://github.com/vllm-project/vllm/security/adv…	x_refsource_CONFIRM
	https://github.com/vllm-project/vllm/pull/12621	x_refsource_MISC
	https://github.com/python/cpython/commit/432117cd…	x_refsource_MISC

Impacted products

	Vendor	Product	Version
	vllm-project	vllm	Affected: < 0.7.2

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2025-25183",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2025-02-07T20:33:57.205558Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2025-02-12T20:51:46.402Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "vllm",
          "vendor": "vllm-project",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.7.2"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. Prefix caching makes use of Python\u0027s built-in hash() function. As of Python 3.12, the behavior of hash(None) has changed to be a predictable constant value. This makes it more feasible that someone could try exploit hash collisions. The impact of a collision would be using cache that was generated using different content. Given knowledge of prompts in use and predictable hashing behavior, someone could intentionally populate the cache using a prompt known to collide with another prompt in use. This issue has been addressed in version 0.7.2 and all users are advised to upgrade. There are no known workarounds for this vulnerability."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "HIGH",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 2.6,
            "baseSeverity": "LOW",
            "confidentialityImpact": "NONE",
            "integrityImpact": "LOW",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:N/I:L/A:N",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-354",
              "description": "CWE-354: Improper Validation of Integrity Check Value",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2025-02-07T19:59:01.370Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-rm76-4mrf-v9r8",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-rm76-4mrf-v9r8"
        },
        {
          "name": "https://github.com/vllm-project/vllm/pull/12621",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/pull/12621"
        },
        {
          "name": "https://github.com/python/cpython/commit/432117cd1f59c76d97da2eaff55a7d758301dbc7",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/python/cpython/commit/432117cd1f59c76d97da2eaff55a7d758301dbc7"
        }
      ],
      "source": {
        "advisory": "GHSA-rm76-4mrf-v9r8",
        "discovery": "UNKNOWN"
      },
      "title": "vLLM using built-in hash() from Python 3.12 leads to predictable hash collisions in vLLM prefix cache"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2025-25183",
    "datePublished": "2025-02-07T19:59:01.370Z",
    "dateReserved": "2025-02-03T19:30:53.399Z",
    "dateUpdated": "2025-02-12T20:51:46.402Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.1"
}

GHSA-RM76-4MRF-V9R8

Vulnerability from github – Published: 2025-02-06 20:00 – Updated: 2025-07-02 14:20

Summary

vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache

Details

Summary

Maliciously constructed prompts can lead to hash collisions, resulting in prefix cache reuse, which can interfere with subsequent responses and cause unintended behavior.

Details

vLLM's prefix caching makes use of Python's built-in hash() function. As of Python 3.12, the behavior of hash(None) has changed to be a predictable constant value. This makes it more feasible that someone could try exploit hash collisions.

Impact

The impact of a collision would be using cache that was generated using different content. Given knowledge of prompts in use and predictable hashing behavior, someone could intentionally populate the cache using a prompt known to collide with another prompt in use.

Solution

We address this problem by initializing hashes in vllm with a value that is no longer constant and predictable. It will be different each time vllm runs. This restores behavior we got in Python versions prior to 3.12.

Using a hashing algorithm that is less prone to collision (like sha256, for example) would be the best way to avoid the possibility of a collision. However, it would have an impact to both performance and memory footprint. Hash collisions may still occur, though they are no longer straight forward to predict.

To give an idea of the likelihood of a collision, for randomly generated hash values (assuming the hash generation built into Python is uniformly distributed), with a cache capacity of 50,000 messages and an average prompt length of 300, a collision will occur on average once every 1 trillion requests.

References

https://github.com/vllm-project/vllm/pull/12621
https://github.com/python/cpython/commit/432117cd1f59c76d97da2eaff55a7d758301dbc7
https://github.com/python/cpython/pull/99541

Severity ?

2.6 (Low)


                  
                    CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:N/I:L/A:N

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "vllm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.7.2"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2025-25183"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-354"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2025-02-06T20:00:05Z",
    "nvd_published_at": "2025-02-07T20:15:34Z",
    "severity": "LOW"
  },
  "details": "### Summary\n\nMaliciously constructed prompts can lead to hash collisions, resulting in prefix cache reuse, which can interfere with subsequent responses and cause unintended behavior.\n\n### Details\n\nvLLM\u0027s prefix caching makes use of Python\u0027s built-in hash() function. As of Python 3.12, the behavior of hash(None) has changed to be a predictable constant value. This makes it more feasible that someone could try exploit hash collisions.\n\n### Impact\n\nThe impact of a collision would be using cache that was generated using different content. Given knowledge of prompts in use and predictable hashing behavior, someone could intentionally populate the cache using a prompt known to collide with another prompt in use. \n\n### Solution\n\nWe address this problem by initializing hashes in vllm with a value that is no longer constant and predictable. It will be different each time vllm runs. This restores behavior we got in Python versions prior to 3.12.\n\nUsing a hashing algorithm that is less prone to collision (like sha256, for example) would be the best way to avoid the possibility of a collision. However, it would have an impact to both performance and memory footprint. Hash collisions may still occur, though they are no longer straight forward to predict.\n\nTo give an idea of the likelihood of a collision, for randomly generated hash values (assuming the hash generation built into Python is uniformly distributed), with a cache capacity of 50,000 messages and an average prompt length of 300, a collision will occur on average once every 1 trillion requests.\n\n### References\n\n* https://github.com/vllm-project/vllm/pull/12621\n* https://github.com/python/cpython/commit/432117cd1f59c76d97da2eaff55a7d758301dbc7\n* https://github.com/python/cpython/pull/99541",
  "id": "GHSA-rm76-4mrf-v9r8",
  "modified": "2025-07-02T14:20:34Z",
  "published": "2025-02-06T20:00:05Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-rm76-4mrf-v9r8"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-25183"
    },
    {
      "type": "WEB",
      "url": "https://github.com/python/cpython/pull/99541"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/12621"
    },
    {
      "type": "WEB",
      "url": "https://github.com/python/cpython/commit/432117cd1f59c76d97da2eaff55a7d758301dbc7"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/commit/73b35cca7f3745d07d439c197768b25d88b6ab7f"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-62.yaml"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/vllm-project/vllm"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:N/I:L/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache"
}

Sightings

Author	Source	Type	Date

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.

Detection rules are retrieved from Rulezet.

Action not permitted

PYSEC-2025-62

CVE-2025-25183 (GCVE-0-2025-25183)

GHSA-RM76-4MRF-V9R8

Summary

Details

Impact

Solution

References

Tags

Sightings

Nomenclature