CVE-2025-6211
July 10, 2025
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.
Affected Packages
https://github.com/run-llama/llama_index.git (GITHUB):
Affected version(s) >=v0.2.17 <v0.12.41Fix Suggestion:
Update to version v0.12.41llama-index-readers-docugami (PYTHON):
Affected version(s) >=0.0.1 <0.3.1Fix Suggestion:
Update to version 0.3.1llama-index-readers-docugami (PYTHON):
Affected version(s) >=0.0.1 <0.3.1Fix Suggestion:
Update to version 0.3.1llama-index (PYTHON):
Affected version(s) >=0.4.4 <0.12.41Fix Suggestion:
Update to version 0.12.41Related ResourcesĀ (4)
Do you need more information?
Contact UsCVSS v4
Base Score:
6.9
Attack Vector
NETWORK
Attack Complexity
LOW
Attack Requirements
NONE
Privileges Required
NONE
User Interaction
NONE
Vulnerable System Confidentiality
NONE
Vulnerable System Integrity
LOW
Vulnerable System Availability
LOW
Subsequent System Confidentiality
NONE
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
6.5
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
NONE
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
NONE
Integrity
LOW
Availability
LOW
Weakness Type (CWE)
Expected Behavior Violation
EPSS
Base Score:
0.06