Vulnerability from drupal
Published
2025-12-03 18:48
Modified
2025-12-03 19:05
Summary
Details

This modules provides the ability to chat with an AI Agent using a large-language model (LLM) provider for different purposes.

The module doesn’t sufficiently filter LLM responses. This leads to a cross-site scripting (XSS) vulnerability where an attacker can use prompt injections on user-generated content with the LLM as context.

Credits
Drew Webber (mcdruid) www.drupal.org/u/mcdruid
To clipboard 

{
  "affected": [
    {
      "database_specific": {
        "affected_versions": "\u003c1.0.7 || \u003e=1.1.0 \u003c1.1.7 || \u003e=1.2.0 \u003c1.2.4"
      },
      "package": {
        "ecosystem": "Packagist:https://packages.drupal.org/8",
        "name": "drupal/ai"
      },
      "ranges": [
        {
          "database_specific": {
            "constraint": "\u003c1.0.7"
          },
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.0.7"
            }
          ],
          "type": "ECOSYSTEM"
        },
        {
          "database_specific": {
            "constraint": "\u003e=1.1.0 \u003c1.1.7"
          },
          "events": [
            {
              "introduced": "1.1.0"
            },
            {
              "fixed": "1.1.7"
            }
          ],
          "type": "ECOSYSTEM"
        },
        {
          "database_specific": {
            "constraint": "\u003e=1.2.0 \u003c1.2.4"
          },
          "events": [
            {
              "introduced": "1.2.0"
            },
            {
              "fixed": "1.2.4"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ],
      "severity": []
    }
  ],
  "aliases": [
    "CVE-2025-13981"
  ],
  "credits": [
    {
      "contact": [
        "https://www.drupal.org/u/mcdruid"
      ],
      "name": "Drew Webber (mcdruid)"
    }
  ],
  "details": "This modules provides the ability to chat with an AI Agent using a large-language model (LLM) provider for different purposes.\n\nThe module doesn\u2019t sufficiently filter LLM responses. This leads to a cross-site scripting (XSS) vulnerability where an attacker can use prompt injections on user-generated content with the LLM as context.",
  "id": "DRUPAL-CONTRIB-2025-119",
  "modified": "2025-12-03T19:05:53.000Z",
  "published": "2025-12-03T18:48:23.000Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://www.drupal.org/sa-contrib-2025-119"
    }
  ],
  "schema_version": "1.7.0"
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




Sightings

Author Source Type Date

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.