Browse / Improper Output Handling / CVE-2024-3271
llama-index-core Command Injection vulnerability
- Class
- Improper Output Handling (filed by a model that read the advisory)
- Technique
- Code and command execution
- Also involves
- Direct Prompt Injection
- Affected
- llama-index-core (PyPI)
- Gets past
- Input filter or sanitiser
- CVSS
- CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- EPSS
- 2.9% chance of exploitation in 30 days
How it works, in short
Input crafted to make the LLM emit code avoids the underscore check in safe_eval, so generated expressions still run OS commands on the server. (Our summary, written by a model. The source text is below.)
Details
A command injection vulnerability exists in the run-llama/llama_index repository, specifically within the safe_eval function. Attackers can bypass the intended security mechanism, which checks for the presence of underscores in code generated by LLM, to execute arbitrary code. This is achieved by crafting input that does not contain an underscore but still results in the execution of OS commands. The vulnerability allows for remote code execution (RCE) on the server hosting the application.
References
- https://nvd.nist.gov/vuln/detail/CVE-2024-3271
- https://github.com/run-llama/llama_index/commit/2c92e88838a5f481d50840240b1dd3180066c6f5
- https://github.com/run-llama/llama_index/commit/5fbcb5a8b9f20f81b791c7fc8849e352613ab475
- https://github.com/pypa/advisory-database/tree/main/vulns/llama-index-core/PYSEC-2026-396.yaml
- https://github.com/run-llama/llama_index
- https://huntr.com/bounties/9b32490e-7cf9-470e-8d49-ba083ae7a279
- https://pypi.org/project/llama-index-core
Source: GitHub Advisory Database, used under CC BY 4.0.