CVE-2025-6211

MD5 Hash Collision in run-llama/llama_index

Published Jul 10, 2025 CVSS 3.0 · 6.5 Medium EPSS < 1% KEV · Not listed
Description
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.

Remediation

No solution or workaround provided in the CVE record

Tracking

Sign in to view the affected projects.

Advisories

Source ID Title
EUVD EUVD EUVD-2025-20993 LlamaIndex vulnerable to data loss through hash collisions in its DocugamiReader class
Github GHSA Github GHSA GHSA-5hq9-5r78-2gjh LlamaIndex vulnerable to data loss through hash collisions in its DocugamiReader class
History
Type Values Removed Values Added
First Time appeared Llamaindex
Llamaindex llamaindex
CPEs cpe:2.3:a:llamaindex:llamaindex:*:*:*:*:*:*:*:*
Vendors & Products Llamaindex
Llamaindex llamaindex
Type Values Removed Values Added
Metrics epss

{'score': 0.00036}

epss

{'score': 0.00048}

Type Values Removed Values Added
Metrics epss

{'score': 0.00036}

Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'yes', 'Exploitation': 'poc', 'Technical Impact': 'partial'}, 'version': '2.0.3'}

Type Values Removed Values Added
Description 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.
Title MD5 Hash Collision in run-llama/llama_index
Weaknesses CWE-440
References
Metrics cvssV3_0

{'score': 6.5, 'vector': 'CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L'}

Weaknesses

Sources

Status
PUBLISHED
Assigner
@huntr_ai
Published
Updated
Jul 10, 2025, 3:13 PM
Reserved
Jun 17, 2025, 5:36 PM
Status
Analyzed
Published
Jul 10, 2025, 1:15 PM
Modified
Jun 17, 2026, 10:01 AM
Severity
Moderate
Public date
Jul 10, 2025, 1:04 PM