(CVE-2026-84911)
Vulnerability from drupal – Published: 2026-09-02 16:26 – Updated: 2026-09-02 16:26 – Source websiteThis AI Chatbot module enables you to have a Chatbot using assistants to help you with your Drupal website.
The module doesn't sufficiently sanitize for cross site scripting (XSS) when using the structured results using legacy agent setups.
This vulnerability is mitigated by the fact that an attacker must be able to invoke a prompt injection set via editorial content and the site must have been setup using AI 1.0.x and AI Agents 1.0.x branch using a uncommon configuration. Any configuration setup or updated after these minor versions are not affected.
| URL | Type | |
|---|---|---|
{
"affected": [
{
"database_specific": {
"affected_versions": "\u003c1.3.13 || \u003e=1.4.0 \u003c1.4.8"
},
"package": {
"ecosystem": "Packagist:https://packages.drupal.org/8",
"name": "drupal/ai"
},
"ranges": [
{
"database_specific": {
"constraint": "\u003c1.3.13"
},
"events": [
{
"introduced": "0"
},
{
"fixed": "1.3.13"
}
],
"type": "ECOSYSTEM"
},
{
"database_specific": {
"constraint": "\u003e=1.4.0 \u003c1.4.8"
},
"events": [
{
"introduced": "1.4.0"
},
{
"fixed": "1.4.8"
}
],
"type": "ECOSYSTEM"
}
],
"severity": []
}
],
"aliases": [
"CVE-2026-84911"
],
"credits": [
{
"contact": [
"https://www.drupal.org/u/mcdruid"
],
"name": "Drew Webber (mcdruid)"
}
],
"details": "This AI Chatbot module enables you to have a Chatbot using assistants to help you with your Drupal website.\n\nThe module doesn\u0027t sufficiently sanitize for cross site scripting (XSS) when using the structured results using legacy agent setups.\n\nThis vulnerability is mitigated by the fact that an attacker must be able to invoke a prompt injection set via editorial content and the site must have been setup using AI 1.0.x and AI Agents 1.0.x branch using a uncommon configuration. Any configuration setup or updated after these minor versions are not affected.",
"id": "DRUPAL-CONTRIB-2026-119",
"modified": "2026-09-02T16:26:41.000Z",
"published": "2026-09-02T16:26:41.000Z",
"references": [
{
"type": "WEB",
"url": "https://www.drupal.org/sa-contrib-2026-119"
}
],
"schema_version": "1.7.0"
}
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.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.