PYSEC-2026-1565

Vulnerability from pysec - Published: 2026-07-07 11:45 - Updated: 2026-07-07 17:24
VLAI
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.

Severity
8.8 (High)
CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Impacted products
Name purl
llama-index-llms-rungpt pkg:pypi/llama-index-llms-rungpt
Aliases
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "llama-index-llms-rungpt",
        "purl": "pkg:pypi/llama-index-llms-rungpt"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.1.3"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ],
      "versions": [
        "0.0.1",
        "0.1.0",
        "0.1.1",
        "0.1.2"
      ]
    }
  ],
  "aliases": [
    "CVE-2024-4181",
    "GHSA-pw38-xv9x-h8ch"
  ],
  "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\u0027s 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.",
  "id": "PYSEC-2026-1565",
  "modified": "2026-07-07T17:24:33.847674Z",
  "published": "2026-07-07T11:45:42.603795Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2024-4181"
    },
    {
      "type": "WEB",
      "url": "https://github.com/run-llama/llama_index/commit/d73715eaf0642705583e7897c78b9c8dd2d3a7ba"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/run-llama/llama_index"
    },
    {
      "type": "WEB",
      "url": "https://huntr.com/bounties/1a204520-598a-434e-b13d-0d34f2a5ddc1"
    },
    {
      "type": "PACKAGE",
      "url": "https://pypi.org/project/llama-index-llms-rungpt"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/advisories/GHSA-pw38-xv9x-h8ch"
    }
  ],
  "severity": [
    {
      "score": "CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "RunGptLLM class in LlamaIndex has a command injection"
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

Sightings

Author Source Type Date Other

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or observed by the user.
  • Confirmed: The vulnerability has been validated from an analyst's perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
  • Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
  • Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
  • Not confirmed: The user expressed doubt about the validity of the vulnerability.
  • Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.


Detection rules are retrieved from Rulezet.