{"id":"CVE-2024-4181","aliases":["GHSA-pw38-xv9x-h8ch","PYSEC-2024-324","PYSEC-2026-1565"],"url":"https://o3.security/vulnerability/CVE-2024-4181","summary":"Command Injection in run-llama/llama_index","details":"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.","published":"2024-05-16T09:03:47.278Z","modified":"2026-08-12T03:51:34.266098266Z","cvss":{"score":8.8,"severity":"HIGH","vector":"CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H"},"epss":{"score":0.02118,"percentile":0.80186,"asOf":"2026-08-23"},"cisaKev":null,"exploitsKnown":0,"affectedPackages":[{"ecosystem":"PyPI","name":"llama-index","fixedVersion":"0.10.13"},{"ecosystem":"PyPI","name":"llama-index-llms-rungpt","fixedVersion":"0.1.3"}],"fix":{"url":"https://github.com/run-llama/llama_index/commit/d73715eaf0642705583e7897c78b9c8dd2d3a7ba","label":"run-llama/llama_index@d73715e"},"references":[{"type":"WEB","url":"https://huntr.com/bounties/1a204520-598a-434e-b13d-0d34f2a5ddc1"},{"type":"ADVISORY","url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2024/4xxx/CVE-2024-4181.json"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2024-4181"},{"type":"FIX","url":"https://github.com/run-llama/llama_index/commit/d73715eaf0642705583e7897c78b9c8dd2d3a7ba"},{"type":"PACKAGE","url":"https://github.com/run-llama/llama_index"}],"provenance":{"sources":["OSV.dev","FIRST.org (EPSS)"],"lastVerified":"2026-08-12T03:51:34.266098266Z"}}