{"cve":"CVE-2024-4181","nvd":{"published":"2024-05-16T09:15:15.553","modified":"2026-06-17T08:01:16.973","status":"Analyzed","description":"A command injection vulnerability exists in the RunGptLLM class of the llama_index library, version 0.9.47, used by the RunGpt framework from JinaAI to connect to Language Learning Models (LLMs). The vulnerability arises from the improper use of the eval function, allowing a malicious or compromised LLM hosting provider to execute arbitrary commands on the client's machine. This issue was fixed in version 0.10.13. The exploitation of this vulnerability could lead to a hosting provider gaining full control over client machines.","cvss_v4":null,"cvss_v3":{"version":"3.0","vector":"CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","score":8.8},"cwes":["CWE-94"],"references":["https://github.com/run-llama/llama_index/commit/d73715eaf0642705583e7897c78b9c8dd2d3a7ba","https://huntr.com/bounties/1a204520-598a-434e-b13d-0d34f2a5ddc1","https://github.com/run-llama/llama_index/commit/d73715eaf0642705583e7897c78b9c8dd2d3a7ba","https://huntr.com/bounties/1a204520-598a-434e-b13d-0d34f2a5ddc1"],"products":["llamaindex:llamaindex"],"source":"nvd","synced_at":"2026-10-19T21:50:30.954589733+00:00"},"epss":{"cve":"CVE-2024-4181","score":0.02135,"percentile":0.8201,"date":"2026-10-31"},"kev":null,"osv":[{"id":"GHSA-pw38-xv9x-h8ch","url":"https://osv.dev/vulnerability/GHSA-pw38-xv9x-h8ch","summary":"RunGptLLM class in LlamaIndex has a command injection","modified":"2026-07-13T07:26:21.243502373Z","packages":[{"ecosystem":"PyPI","name":"llama-index","purl":"pkg:pypi/llama-index","ranges":["<0.10.13"],"fixed":["0.10.13"]},{"ecosystem":"PyPI","name":"llama-index-llms-rungpt","purl":"pkg:pypi/llama-index-llms-rungpt","ranges":["<0.1.3"],"fixed":["0.1.3"]}]},{"id":"PYSEC-2024-324","url":"https://osv.dev/vulnerability/PYSEC-2024-324","summary":"","modified":"2026-07-13T07:26:21.243502373Z","packages":[{"ecosystem":"PyPI","name":"llama-index","purl":"pkg:pypi/llama-index","ranges":[">=0.9.47 <0.10.13"],"fixed":["0.10.13"]}]},{"id":"PYSEC-2026-1565","url":"https://osv.dev/vulnerability/PYSEC-2026-1565","summary":"RunGptLLM class in LlamaIndex has a command injection","modified":"2026-07-13T07:26:21.243502373Z","packages":[{"ecosystem":"PyPI","name":"llama-index-llms-rungpt","purl":"pkg:pypi/llama-index-llms-rungpt","ranges":["<0.1.3"],"fixed":["0.1.3"]}]}],"attribution":["This product uses the NVD API but is not endorsed or certified by the NVD.","EPSS scores: FIRST Exploit Prediction Scoring System, https://www.first.org/epss","Known exploited vulnerabilities: CISA Known Exploited Vulnerabilities Catalog, https://www.cisa.gov/known-exploited-vulnerabilities-catalog","Package advisories: OSV (https://osv.dev), from the GitHub Advisory Database, PyPA, Go, RustSec and other ecosystem databases, under CC-BY 4.0 or CC0","CVE records: the CVE Program's CVE List (https://www.cve.org), under its terms of use (https://www.cve.org/Legal/TermsOfUse). CVE is a registered trademark of The MITRE Corporation; this product is not affiliated with the CVE Program."]}