Medium severity6.5NVD Advisory· Published Jul 10, 2025· Updated Jun 17, 2026
CVE-2025-6211
CVE-2025-6211
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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected packages
Versions sourced from the GitHub Security Advisory.
| Package | Affected versions | Patched versions |
|---|---|---|
llama-indexPyPI | < 0.12.41 | 0.12.41 |
llama-index-readers-docugamiPyPI | < 0.3.1 | 0.3.1 |
Affected products
5- osv-coords3 versions
< 2.3.2-r1+ 2 more
- (no CPE)range: < 2.3.2-r1
- (no CPE)range: < 0.12.41
- (no CPE)range: < 0.3.1
- Range: unspecified
Patches
Vulnerability mechanics
References
4- github.com/run-llama/llama_index/commit/29b2e07e64ed7d302b1cc058185560b28eaa1352nvdPatchWEB
- huntr.com/bounties/1a48a011-a3c5-4979-9ffc-9652280bc389nvdExploitThird Party AdvisoryWEB
- github.com/advisories/GHSA-5hq9-5r78-2gjhghsaADVISORY
- nvd.nist.gov/vuln/detail/CVE-2025-6211ghsaADVISORY
News mentions
0No linked articles in our index yet.