Description (CNA)
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 (CNA)
| Vendor / product | Versions |
|---|---|
| run-llama / run-llama/llama_index | affected unspecified before 0.3.1 |
CWE
CWE-440
References
- https://huntr.com/bounties/1a48a011-a3c5-4979-9ffc-9652280bc389
- https://github.com/run-llama/llama_index/commit/29b2e07e64ed7d302b1cc058185560b28eaa1352
ADP enrichment
No English description supplied.