Vulnerability-Lookup

GHSA-898V-775G-777C

Vulnerability from github – Published: 2025-12-09 17:19 – Updated: 2025-12-11 15:49

Summary

Neuron MySQLWriteTool allows arbitrary/destructive SQL when exposed to untrusted prompts (agent “footgun”)

Details

Impact

MySQLWriteTool executes arbitrary SQL provided by the caller using PDO::prepare() + execute() without semantic restrictions.

This is consistent with the name (“write tool”), but in an LLM/agent context it becomes a high-risk capability: prompt injection or indirect prompt manipulation can cause execution of destructive queries such as DROP TABLE, TRUNCATE, DELETE, ALTER, or privilege-related statements (subject to DB permissions).

Who is impacted: Deployments that expose an agent with MySQLWriteTool enabled to untrusted input and/or run the tool with a DB user that has broad privileges.

Patches

Not patched in: 2.8.11

Recommended improvements (even if keeping the tool intentionally powerful):

Provide a safer API that supports only constrained operations (e.g., insertRecord, updateRecord) with allowlisted tables/columns.
Add a policy/allowlist layer (e.g., allow only INSERT/UPDATE on selected tables; forbid DROP/TRUNCATE/ALTER/GRANT).
Add optional review workflow: log + require human approval for high-risk statements; or “dry-run” mode.
Document strongly that the tool must not be exposed to untrusted prompts without additional safeguards.

Workarounds

Do not enable MySQLWriteTool for public/untrusted agents.
Use a dedicated DB user with least privilege:
no DROP, no ALTER, no GRANT, no access to sensitive tables unless necessary
Add an application-layer policy rejecting high-risk statements (DROP, TRUNCATE, ALTER, GRANT, REVOKE, CREATE USER, etc.).
Implement authorization gating for tool calls (RBAC, allow tool use only for trusted operators).

Severity

9.4 (Critical)


                  
                    CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:H

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "database_specific": {
        "last_known_affected_version_range": "\u003c= 2.8.11"
      },
      "package": {
        "ecosystem": "Packagist",
        "name": "neuron-core/neuron-ai"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "2.8.12"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2025-67510"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-250",
      "CWE-284"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2025-12-09T17:19:42Z",
    "nvd_published_at": "2025-12-10T23:15:48Z",
    "severity": "CRITICAL"
  },
  "details": "### Impact\n\n`MySQLWriteTool` executes arbitrary SQL provided by the caller using `PDO::prepare()` + `execute()` without semantic restrictions.  \n\nThis is consistent with the name (\u201cwrite tool\u201d), but in an LLM/agent context it becomes a high-risk capability: prompt injection or indirect prompt manipulation can cause execution of destructive queries such as `DROP TABLE`, `TRUNCATE`, `DELETE`, `ALTER`, or privilege-related statements (subject to DB permissions).\n\n\n\n**Who is impacted:** Deployments that expose an agent with `MySQLWriteTool` enabled to untrusted input and/or run the tool with a DB user that has broad privileges.\n\n### Patches\n\n**Not patched in:** 2.8.11  \n\nRecommended improvements (even if keeping the tool intentionally powerful):\n\n- Provide a safer API that supports only constrained operations (e.g., `insertRecord`, `updateRecord`) with allowlisted tables/columns.\n\n- Add a policy/allowlist layer (e.g., allow only `INSERT`/`UPDATE` on selected tables; forbid `DROP/TRUNCATE/ALTER/GRANT`).\n\n- Add optional review workflow: log + require human approval for high-risk statements; or \u201cdry-run\u201d mode.\n\n- Document strongly that the tool must not be exposed to untrusted prompts without additional safeguards.\n\n\n\n### Workarounds\n\n- Do not enable `MySQLWriteTool` for public/untrusted agents.\n\n- Use a dedicated DB user with **least privilege**:\n\n  - no `DROP`, no `ALTER`, no `GRANT`, no access to sensitive tables unless necessary\n\n- Add an application-layer policy rejecting high-risk statements (`DROP`, `TRUNCATE`, `ALTER`, `GRANT`, `REVOKE`, `CREATE USER`, etc.).\n\n- Implement authorization gating for tool calls (RBAC, allow tool use only for trusted operators).",
  "id": "GHSA-898v-775g-777c",
  "modified": "2025-12-11T15:49:17Z",
  "published": "2025-12-09T17:19:42Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/neuron-core/neuron-ai/security/advisories/GHSA-898v-775g-777c"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-67510"
    },
    {
      "type": "WEB",
      "url": "https://github.com/neuron-core/neuron-ai/commit/44bab85d92bf162898ee48d0bcef6ba0d29b59c9"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/neuron-core/neuron-ai"
    },
    {
      "type": "WEB",
      "url": "https://github.com/neuron-core/neuron-ai/releases/tag/2.8.12"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Neuron MySQLWriteTool allows arbitrary/destructive SQL when exposed to untrusted prompts (agent \u201cfootgun\u201d)"
}

CVE-2025-67510 (GCVE-0-2025-67510)

Vulnerability from cvelistv5 – Published: 2025-12-10 22:55 – Updated: 2025-12-11 15:37

Title

MySQLWriteTool allows arbitrary/destructive SQL when exposed to untrusted prompts (agent “footgun”)

Summary

Neuron is a PHP framework for creating and orchestrating AI Agents. In versions 2.8.11 and below, the MySQLWriteTool executes arbitrary SQL provided by the caller using PDO::prepare() + execute() without semantic restrictions. This is consistent with the name (“write tool”), but in an LLM/agent context it becomes a high-risk capability: prompt injection or indirect prompt manipulation can cause execution of destructive queries such as DROP TABLE, TRUNCATE, DELETE, ALTER, or privilege-related statements (subject to DB permissions). Deployments that expose an agent with MySQLWriteTool enabled to untrusted input and/or run the tool with a DB user that has broad privileges are impacted. This issue is fixed in version 2.8.12.

Severity

9.4 (Critical)


                        
                          CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:H

SSVC

Exploitation: none Automatable: yes Technical Impact: partial

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2025-12-11 15:37 UTC

CWE

CWE-250 - Execution with Unnecessary Privileges
CWE-284 - Improper Access Control

Assigner

GitHub_M mitre root

References

3 references

URL	Tags
https://github.com/neuron-core/neuron-ai/security…	x_refsource_CONFIRM
https://github.com/neuron-core/neuron-ai/commit/4…	x_refsource_MISC
https://github.com/neuron-core/neuron-ai/releases…	x_refsource_MISC

Impacted products

1 product

Vendor	Product	Version
neuron-core	neuron-ai	Affected: < 2.8.12

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2025-67510",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2025-12-11T15:37:23.715344Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2025-12-11T15:37:39.220Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "neuron-ai",
          "vendor": "neuron-core",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 2.8.12"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "Neuron is a PHP framework for creating and orchestrating AI Agents. In versions 2.8.11 and below, the MySQLWriteTool executes arbitrary SQL provided by the caller using PDO::prepare() + execute() without semantic restrictions. This is consistent with the name (\u201cwrite tool\u201d), but in an LLM/agent context it becomes a high-risk capability: prompt injection or indirect prompt manipulation can cause execution of destructive queries such as DROP TABLE, TRUNCATE, DELETE, ALTER, or privilege-related statements (subject to DB permissions). Deployments that expose an agent with MySQLWriteTool enabled to untrusted input and/or run the tool with a DB user that has broad privileges are impacted. This issue is fixed in version 2.8.12."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 9.4,
            "baseSeverity": "CRITICAL",
            "confidentialityImpact": "LOW",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:H",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-250",
              "description": "CWE-250: Execution with Unnecessary Privileges",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-284",
              "description": "CWE-284: Improper Access Control",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2025-12-10T23:06:33.728Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/neuron-core/neuron-ai/security/advisories/GHSA-898v-775g-777c",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/neuron-core/neuron-ai/security/advisories/GHSA-898v-775g-777c"
        },
        {
          "name": "https://github.com/neuron-core/neuron-ai/commit/44bab85d92bf162898ee48d0bcef6ba0d29b59c9",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/neuron-core/neuron-ai/commit/44bab85d92bf162898ee48d0bcef6ba0d29b59c9"
        },
        {
          "name": "https://github.com/neuron-core/neuron-ai/releases/tag/2.8.12",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/neuron-core/neuron-ai/releases/tag/2.8.12"
        }
      ],
      "source": {
        "advisory": "GHSA-898v-775g-777c",
        "discovery": "UNKNOWN"
      },
      "title": "MySQLWriteTool allows arbitrary/destructive SQL when exposed to untrusted prompts (agent \u201cfootgun\u201d)"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2025-67510",
    "datePublished": "2025-12-10T22:55:21.253Z",
    "dateReserved": "2025-12-08T21:46:24.993Z",
    "dateUpdated": "2025-12-11T15:37:39.220Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

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 MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base model, served locally by ML-Gateway. They have not been verified by an analyst and are provided for guidance only.
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.

Action not permitted