Browse / Improper Output Handling / CVE-2024-12911
LlamaIndex vulnerable to Creation of Temporary File in Directory with Insecure Permissions
- Class
- Improper Output Handling (filed by a model that read the advisory)
- Technique
- SQL and query injection
- Also involves
- Direct Prompt Injection
- Affected
- llama-index (PyPI)
- CVSS
- CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:L/A:H
- EPSS
- 0.5% chance of exploitation in 30 days
How it works, in short
Crafted natural-language queries make the engine's LLM produce SQL that the JSON analysis function runs without safe handling. (Our summary, written by a model. The source text is below.)
Details
A vulnerability in the default_jsonalyzer function of the JSONalyzeQueryEngine in the run-llama/llama_index repository allows for SQL injection via prompt injection. This can lead to arbitrary file creation and Denial-of-Service (DoS) attacks. The vulnerability affects the latest version and is fixed in version 0.12.3.
References
- https://nvd.nist.gov/vuln/detail/CVE-2024-12911
- https://github.com/run-llama/llama_index/commit/bf282074e20e7dafd5e2066137dcd4cd17c3fb9e
- https://github.com/run-llama/llama_index
- https://huntr.com/bounties/095f9e67-311d-494c-99c5-5e61a0adb8f3
Source: GitHub Advisory Database, used under CC BY 4.0.