GHSA-49F7-WHX5-4256

Vulnerability from github – Published: 2026-07-07 21:31 – Updated: 2026-09-03 20:10
VLAI
Summary
Cognee allows non-superusers to overwrite global LLM configuration
Details

Cognee before 1.2.0 contains an improper access control vulnerability that allows unauthenticated attackers to overwrite the global LLM provider configuration by self-registering an account and calling the settings endpoint, which performs no admin or superuser check. Attackers can redirect all LLM operations instance-wide to an attacker-controlled endpoint by exploiting the process-wide singleton configuration cache, enabling exfiltration of prompts, uploaded documents, extracted entities, and knowledge graph content from all users.

Severity
9.1 (Critical)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N
9.3 (Critical)
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "cognee"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.5.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-58473"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-306"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-09-03T20:10:21Z",
    "nvd_published_at": "2026-07-07T21:17:29Z",
    "severity": "CRITICAL"
  },
  "details": "Cognee before 1.2.0 contains an improper access control vulnerability that allows unauthenticated attackers to overwrite the global LLM provider configuration by self-registering an account and calling the settings endpoint, which performs no admin or superuser check. Attackers can redirect all LLM operations instance-wide to an attacker-controlled endpoint by exploiting the process-wide singleton configuration cache, enabling exfiltration of prompts, uploaded documents, extracted entities, and knowledge graph content from all users.",
  "id": "GHSA-49f7-whx5-4256",
  "modified": "2026-09-03T20:10:21Z",
  "published": "2026-07-07T21:31:36Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-58473"
    },
    {
      "type": "WEB",
      "url": "https://github.com/topoteretes/cognee/issues/3084"
    },
    {
      "type": "WEB",
      "url": "https://github.com/topoteretes/cognee/commit/10971db1b0bd97e88f96bd2a9ffb3edb7b22bcd0"
    },
    {
      "type": "WEB",
      "url": "https://github.com/topoteretes/cognee/commit/d10b1b77e2157c6238fd4d1acb1923a048991699"
    },
    {
      "type": "WEB",
      "url": "https://github.com/topoteretes/cognee/commit/ebcf82412d0954f5c5018444f7eee8d96fee5113"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/topoteretes/cognee"
    },
    {
      "type": "WEB",
      "url": "https://github.com/topoteretes/cognee/releases/tag/v1.2.0"
    },
    {
      "type": "WEB",
      "url": "https://www.vulncheck.com/advisories/cognee-unauthorized-llm-configuration-overwrite-via-api-v1-settings"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N",
      "type": "CVSS_V4"
    }
  ],
  "summary": "Cognee allows non-superusers to overwrite global LLM configuration"
}



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.



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.