Vulnerability-Lookup

PYSEC-2026-1566

Vulnerability from pysec - Published: 2026-07-07 16:02 - Updated: 2026-07-07 17:24

Details

A vulnerability in the DocugamiReader class of the run-llama/llama_index repository, up to but excluding version 0.12.41, involves the use of MD5 hashing to generate IDs for document chunks. This approach leads to hash collisions when structurally distinct chunks contain identical text, resulting in one chunk overwriting another. This can cause loss of semantically or legally important document content, breakage of parent-child chunk hierarchies, and inaccurate or hallucinated responses in AI outputs. The issue is resolved in version 0.3.1.

Severity

6.5 (Medium)


                  
                    CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L

Impacted products

Name	purl
llama-index-readers-docugami	pkg:pypi/llama-index-readers-docugami

Aliases

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "llama-index-readers-docugami",
        "purl": "pkg:pypi/llama-index-readers-docugami"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.3.1"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ],
      "versions": [
        "0.0.1",
        "0.0.2",
        "0.1.0",
        "0.1.1",
        "0.1.2",
        "0.1.3",
        "0.1.4",
        "0.2.0",
        "0.3.0"
      ]
    }
  ],
  "aliases": [
    "CVE-2025-6211",
    "GHSA-5hq9-5r78-2gjh"
  ],
  "details": "A vulnerability in the DocugamiReader class of the run-llama/llama_index repository, up to but excluding version 0.12.41, involves the use of MD5 hashing to generate IDs for document chunks. This approach leads to hash collisions when structurally distinct chunks contain identical text, resulting in one chunk overwriting another. This can cause loss of semantically or legally important document content, breakage of parent-child chunk hierarchies, and inaccurate or hallucinated responses in AI outputs. The issue is resolved in version 0.3.1.",
  "id": "PYSEC-2026-1566",
  "modified": "2026-07-07T17:24:33.960930Z",
  "published": "2026-07-07T16:02:57.492463Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-6211"
    },
    {
      "type": "WEB",
      "url": "https://github.com/run-llama/llama_index/commit/29b2e07e64ed7d302b1cc058185560b28eaa1352"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/run-llama/llama_index"
    },
    {
      "type": "WEB",
      "url": "https://huntr.com/bounties/1a48a011-a3c5-4979-9ffc-9652280bc389"
    },
    {
      "type": "PACKAGE",
      "url": "https://pypi.org/project/llama-index-readers-docugami"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/advisories/GHSA-5hq9-5r78-2gjh"
    }
  ],
  "severity": [
    {
      "score": "CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L",
      "type": "CVSS_V3"
    }
  ],
  "summary": "LlamaIndex vulnerable to data loss through hash collisions in its DocugamiReader class "
}

CVE-2025-6211 (GCVE-0-2025-6211)

Vulnerability from cvelistv5 – Published: 2025-07-10 13:04 – Updated: 2025-07-10 15:13

Title

MD5 Hash Collision in run-llama/llama_index

Summary

A vulnerability in the DocugamiReader class of the run-llama/llama_index repository, up to version 0.12.28, involves the use of MD5 hashing to generate IDs for document chunks. This approach leads to hash collisions when structurally distinct chunks contain identical text, resulting in one chunk overwriting another. This can cause loss of semantically or legally important document content, breakage of parent-child chunk hierarchies, and inaccurate or hallucinated responses in AI outputs. The issue is resolved in version 0.3.1.

Severity

6.5 (Medium)


                        
                          CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L

SSVC

Exploitation: poc Automatable: yes Technical Impact: partial

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2025-07-10 15:13 UTC

CWE

CWE-440 - Expected Behavior Violation

Assigner

@huntr_ai mitre root

References

2 references

URL	Tags
https://huntr.com/bounties/1a48a011-a3c5-4979-9ff…
https://github.com/run-llama/llama_index/commit/2…

Impacted products

1 product

Vendor	Product	Version
run-llama	run-llama/llama_index	Affected: unspecified , < 0.3.1 (custom)

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2025-6211",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2025-07-10T15:13:09.766316Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2025-07-10T15:13:12.599Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://huntr.com/bounties/1a48a011-a3c5-4979-9ffc-9652280bc389"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "run-llama/llama_index",
          "vendor": "run-llama",
          "versions": [
            {
              "lessThan": "0.3.1",
              "status": "affected",
              "version": "unspecified",
              "versionType": "custom"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "A vulnerability in the DocugamiReader class of the run-llama/llama_index repository, up to version 0.12.28, involves the use of MD5 hashing to generate IDs for document chunks. This approach leads to hash collisions when structurally distinct chunks contain identical text, resulting in one chunk overwriting another. This can cause loss of semantically or legally important document content, breakage of parent-child chunk hierarchies, and inaccurate or hallucinated responses in AI outputs. The issue is resolved in version 0.3.1."
        }
      ],
      "metrics": [
        {
          "cvssV3_0": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "LOW",
            "baseScore": 6.5,
            "baseSeverity": "MEDIUM",
            "confidentialityImpact": "NONE",
            "integrityImpact": "LOW",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L",
            "version": "3.0"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-440",
              "description": "CWE-440 Expected Behavior Violation",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2025-07-10T13:04:34.401Z",
        "orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
        "shortName": "@huntr_ai"
      },
      "references": [
        {
          "url": "https://huntr.com/bounties/1a48a011-a3c5-4979-9ffc-9652280bc389"
        },
        {
          "url": "https://github.com/run-llama/llama_index/commit/29b2e07e64ed7d302b1cc058185560b28eaa1352"
        }
      ],
      "source": {
        "advisory": "1a48a011-a3c5-4979-9ffc-9652280bc389",
        "discovery": "EXTERNAL"
      },
      "title": "MD5 Hash Collision in run-llama/llama_index"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
    "assignerShortName": "@huntr_ai",
    "cveId": "CVE-2025-6211",
    "datePublished": "2025-07-10T13:04:34.401Z",
    "dateReserved": "2025-06-17T17:36:01.333Z",
    "dateUpdated": "2025-07-10T15:13:12.599Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.1"
}

GHSA-5HQ9-5R78-2GJH

Vulnerability from github – Published: 2025-07-10 15:31 – Updated: 2025-07-10 18:45

Summary

LlamaIndex vulnerable to data loss through hash collisions in its DocugamiReader class

Details

Severity

6.5 (Medium)


                  
                    CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "llama-index"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.12.41"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "llama-index-readers-docugami"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.3.1"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2025-6211"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-440"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2025-07-10T18:45:04Z",
    "nvd_published_at": "2025-07-10T13:15:23Z",
    "severity": "MODERATE"
  },
  "details": "A vulnerability in the DocugamiReader class of the run-llama/llama_index repository, up to but excluding version 0.12.41, involves the use of MD5 hashing to generate IDs for document chunks. This approach leads to hash collisions when structurally distinct chunks contain identical text, resulting in one chunk overwriting another. This can cause loss of semantically or legally important document content, breakage of parent-child chunk hierarchies, and inaccurate or hallucinated responses in AI outputs. The issue is resolved in version 0.3.1.",
  "id": "GHSA-5hq9-5r78-2gjh",
  "modified": "2025-07-10T18:45:04Z",
  "published": "2025-07-10T15:31:27Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-6211"
    },
    {
      "type": "WEB",
      "url": "https://github.com/run-llama/llama_index/commit/29b2e07e64ed7d302b1cc058185560b28eaa1352"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/run-llama/llama_index"
    },
    {
      "type": "WEB",
      "url": "https://huntr.com/bounties/1a48a011-a3c5-4979-9ffc-9652280bc389"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L",
      "type": "CVSS_V3"
    }
  ],
  "summary": "LlamaIndex vulnerable to data loss through hash collisions in its DocugamiReader class "
}

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.

Detection rules are retrieved from Rulezet.

The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base model, served locally by ML-Gateway. They have not been verified by an analyst and are provided for guidance only.
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.

Action not permitted

PYSEC-2026-1566

CVE-2025-6211 (GCVE-0-2025-6211)

GHSA-5HQ9-5R78-2GJH

Tags

Sightings

Nomenclature

Related by attack behaviour