Vulnerability-Lookup

GHSA-4H5R-5JM8-JXJM

Vulnerability from github – Published: 2026-06-18 20:44 – Updated: 2026-06-18 20:44

Summary

gemini-mcp-tool vulnerable to OS command injection and @file exfiltration via prompt quoting (CVE-2026-0755)

Details

Untrusted prompt input could reach the Gemini CLI @file parser, allowing read/exfiltration of arbitrary local files (@/etc/passwd, @~/.ssh/id_rsa, @../../secret). On Windows, unquoted cmd.exe metacharacters could break out into OS command injection.

Fix (1.1.6): removed the broken shell:false double-quote wrapping; added assertSafeFileReferences() to contain @file refs to the working directory; hardened Windows cmd.exe argument quoting.

Severity

9.8 (Critical)


                  
                    CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "npm",
        "name": "gemini-mcp-tool"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "1.1.2"
            },
            {
              "fixed": "1.1.6"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-0755"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-78"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-06-18T20:44:58Z",
    "nvd_published_at": null,
    "severity": "CRITICAL"
  },
  "details": "Untrusted prompt input could reach the Gemini CLI @file parser, allowing read/exfiltration of arbitrary local files (@/etc/passwd, @~/.ssh/id_rsa, @../../secret). On Windows, unquoted cmd.exe metacharacters could break out into OS command injection.\n\nFix (1.1.6): removed the broken shell:false double-quote wrapping; added assertSafeFileReferences() to contain @file refs to the working directory; hardened Windows cmd.exe argument quoting.",
  "id": "GHSA-4h5r-5jm8-jxjm",
  "modified": "2026-06-18T20:44:58Z",
  "published": "2026-06-18T20:44:58Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/jamubc/gemini-mcp-tool/security/advisories/GHSA-4h5r-5jm8-jxjm"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-0755"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/jamubc/gemini-mcp-tool"
    },
    {
      "type": "WEB",
      "url": "https://www.zerodayinitiative.com/advisories/ZDI-26-021"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "gemini-mcp-tool vulnerable to OS command injection and @file exfiltration via prompt quoting (CVE-2026-0755)"
}

CVE-2026-0755 (GCVE-0-2026-0755)

Vulnerability from cvelistv5 – Published: 2026-01-23 03:26 – Updated: 2026-01-23 19:35

Title

gemini-mcp-tool execAsync Command Injection Remote Code Execution Vulnerability

Summary

gemini-mcp-tool execAsync Command Injection Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of gemini-mcp-tool. Authentication is not required to exploit this vulnerability. The specific flaw exists within the implementation of the execAsync method. The issue results from the lack of proper validation of a user-supplied string before using it to execute a system call. An attacker can leverage this vulnerability to execute code in the context of the service account. Was ZDI-CAN-27783.

Severity

9.8 (Critical)


                        
                          CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

SSVC

Exploitation: none Automatable: yes Technical Impact: total

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2026-01-23 19:34 UTC

CWE

CWE-78 - Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')

Assigner

zdi mitre root Scorecard

References

1 reference

URL	Tags
https://www.zerodayinitiative.com/advisories/ZDI-…	x_research-advisory

Impacted products

1 product

Vendor	Product	Version
Gemini MCP Tool	gemini-mcp-tool	Affected: 1.1.2

Date Public

2026-01-09 16:17

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-0755",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-01-23T19:34:56.695313Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-01-23T19:35:07.197Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "defaultStatus": "unknown",
          "product": "gemini-mcp-tool",
          "vendor": "Gemini MCP Tool",
          "versions": [
            {
              "status": "affected",
              "version": "1.1.2"
            }
          ]
        }
      ],
      "dateAssigned": "2026-01-08T22:49:24.928Z",
      "datePublic": "2026-01-09T16:17:16.515Z",
      "descriptions": [
        {
          "lang": "en",
          "value": "gemini-mcp-tool execAsync Command Injection Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of gemini-mcp-tool. Authentication is not required to exploit this vulnerability.\n\nThe specific flaw exists within the implementation of the execAsync method. The issue results from the lack of proper validation of a user-supplied string before using it to execute a system call. An attacker can leverage this vulnerability to execute code in the context of the service account. Was ZDI-CAN-27783."
        }
      ],
      "metrics": [
        {
          "cvssV3_0": {
            "baseScore": 9.8,
            "baseSeverity": "CRITICAL",
            "vectorString": "CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
            "version": "3.0"
          },
          "format": "CVSS"
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-78",
              "description": "CWE-78: Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-01-23T03:26:16.000Z",
        "orgId": "99f1926a-a320-47d8-bbb5-42feb611262e",
        "shortName": "zdi"
      },
      "references": [
        {
          "name": "ZDI-26-021",
          "tags": [
            "x_research-advisory"
          ],
          "url": "https://www.zerodayinitiative.com/advisories/ZDI-26-021/"
        }
      ],
      "source": {
        "lang": "en",
        "value": "Peter Girnus (@gothburz) of Trend Research"
      },
      "title": "gemini-mcp-tool execAsync Command Injection Remote Code Execution Vulnerability"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "99f1926a-a320-47d8-bbb5-42feb611262e",
    "assignerShortName": "zdi",
    "cveId": "CVE-2026-0755",
    "datePublished": "2026-01-23T03:26:16.000Z",
    "dateReserved": "2026-01-08T22:49:24.875Z",
    "dateUpdated": "2026-01-23T19:35:07.197Z",
    "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

GHSA-4H5R-5JM8-JXJM

CVE-2026-0755 (GCVE-0-2026-0755)

Tags

Sightings

Nomenclature

Related by attack behaviour