AI agent vulnerability · LlamaIndex

CVE-2025-7647: llama-index-core insecurely handles temporary files

highCVSS 3.0 7.3GHSA-cr7q-2w66-hjcm

The llama-index-core package, up to version 0.12.44, contains a vulnerability in the getcachedir() function where a predictable, hardcoded directory path /tmp/llamaindex is used on Linux systems without proper security controls. This vulnerability allows attackers on multi-user systems to steal proprietary models, poison cached embeddings, or conduct symlink attacks.

Published Sep 27, 2025 · Updated Sep 29, 2025

Affected packages

llama-index-core

Ecosystem: PyPI
Affected: < 0.13.0
Fixed in: 0.13.0
Check: pip show llama-index-core

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

The llama-index-core package, up to version 0.12.44, contains a vulnerability in the get_cache_dir() function where a predictable, hardcoded directory path /tmp/llama_index is used on Linux systems without proper security controls. This vulnerability allows attackers on multi-user systems to steal proprietary models, poison cached embeddings, or conduct symlink attacks. The issue affects all Linux deployments where multiple users share the same system. The vulnerability is classified under CWE-379, CWE-377, and CWE-367, indicating insecure temporary file creation and potential race conditions.

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More LlamaIndex vulnerabilities

All LlamaIndex entries