Browse / AI Framework and Platform Flaws / CVE-2025-6208
llama-index-core vulnerable to Uncontrolled Resource Consumption
- Class
- AI Framework and Platform Flaws (filed by a model that read the advisory)
- Technique
- Denial of service
- Affected
- llama-index-core (PyPI)
- CVSS
- CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L
- EPSS
- 0.4% chance of exploitation in 30 days
How it works, in short
The directory reader loads every file into memory before applying the file count limit, so large directories exhaust memory. (Our summary, written by a model. The source text is below.)
Details
The SimpleDirectoryReader component in llama_index.core version 0.12.23 suffers from uncontrolled memory consumption due to a resource management flaw. The vulnerability arises because the user-specified file limit (num_files_limit) is applied after all files in a directory are loaded into memory. This can lead to memory exhaustion and degraded performance, particularly in environments with limited resources. The issue is resolved in version 0.12.41.
References
- https://nvd.nist.gov/vuln/detail/CVE-2025-6208
- https://github.com/run-llama/llama_index/commit/53614e2f7913c0e86b58add9470b3c900b6c60b2
- https://github.com/run-llama/llama_index
- https://huntr.com/bounties/7d722bb6-6567-4608-8b23-f95048d7605a
Source: GitHub Advisory Database, used under CC BY 4.0.