Vulnerability-Lookup

GHSA-87G7-76GR-73G8

Vulnerability from github – Published: 2026-09-26 03:30 – Updated: 2026-09-26 03:30

Details

OpenClaw (npm package openclaw) before 2026.7.1 fails to enforce the owner-only authorization requirement for Claude Code permission prompts delivered through the MCP channel bridge. An authorized non-owner channel sender with channel command access can approve or deny a pending permission request intended for the owner, causing the requested action to proceed without owner consent. The practical impact depends on the pending action and the host capabilities requested by the Claude Code run. The issue is fixed in version 2026.7.1.

Severity

8.0 (High)


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

8.6 (High)


                  
                    CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

Show details on source website

JSON

To clipboard

{
  "affected": [],
  "aliases": [
    "CVE-2026-100585"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-862"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-09-26T03:17:06Z",
    "severity": "HIGH"
  },
  "details": "OpenClaw (npm package `openclaw`) before 2026.7.1 fails to enforce the owner-only authorization requirement for Claude Code permission prompts delivered through the MCP channel bridge. An authorized non-owner channel sender with channel command access can approve or deny a pending permission request intended for the owner, causing the requested action to proceed without owner consent. The practical impact depends on the pending action and the host capabilities requested by the Claude Code run. The issue is fixed in version 2026.7.1.",
  "id": "GHSA-87g7-76gr-73g8",
  "modified": "2026-09-26T03:30:27Z",
  "published": "2026-09-26T03:30:27Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/openclaw/openclaw/security/advisories/GHSA-p5g8-m35v-7m82"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-100585"
    },
    {
      "type": "WEB",
      "url": "https://www.vulncheck.com/advisories/openclaw-before-2026.7.1-authentication-bypass-via-mcp-channel"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
      "type": "CVSS_V4"
    }
  ]
}

CVE-2026-100585 (GCVE-0-2026-100585)

Vulnerability from cvelistv5 – Published: 2026-09-26 02:19 – Updated: 2026-09-26 02:19

Title

OpenClaw before 2026.7.1 Authentication Bypass via MCP Channel

Summary

OpenClaw (npm package `openclaw`) before 2026.7.1 fails to enforce the owner-only authorization requirement for Claude Code permission prompts delivered through the MCP channel bridge. An authorized non-owner channel sender with channel command access can approve or deny a pending permission request intended for the owner, causing the requested action to proceed without owner consent. The practical impact depends on the pending action and the host capabilities requested by the Claude Code run. The issue is fixed in version 2026.7.1.

Severity

8.6 (High)


                        
                          CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

8 (High)


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

CWE

CWE-862 - Missing Authorization

Assigner

VulnCheck mitre root

References

2 references

URL	Tags
https://github.com/openclaw/openclaw/security/adv…	vendor-advisory
https://www.vulncheck.com/advisories/openclaw-bef…	third-party-advisory

Impacted products

1 product

Vendor	Product	Version
OpenClaw	OpenClaw	Affected: 0 , < 2026.7.1 (semver) Unaffected: 2026.7.1 (semver) cpe:2.3:a:openclaw:openclaw::::::::

Date Public

2026-09-11 00:00

Credits

whyiug

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "cna": {
      "affected": [
        {
          "defaultStatus": "unaffected",
          "packageURL": "pkg:npm/openclaw",
          "product": "OpenClaw",
          "vendor": "OpenClaw",
          "versions": [
            {
              "lessThan": "2026.7.1",
              "status": "affected",
              "version": "0",
              "versionType": "semver"
            },
            {
              "status": "unaffected",
              "version": "2026.7.1",
              "versionType": "semver"
            }
          ]
        }
      ],
      "cpeApplicability": [
        {
          "nodes": [
            {
              "cpeMatch": [
                {
                  "criteria": "cpe:2.3:a:openclaw:openclaw:*:*:*:*:*:*:*:*",
                  "versionEndExcluding": "2026.7.1",
                  "vulnerable": true
                }
              ],
              "negate": false,
              "operator": "OR"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "reporter",
          "value": "whyiug"
        }
      ],
      "datePublic": "2026-09-11T00:00:00.000Z",
      "descriptions": [
        {
          "lang": "en",
          "value": "OpenClaw (npm package `openclaw`) before 2026.7.1 fails to enforce the owner-only authorization requirement for Claude Code permission prompts delivered through the MCP channel bridge. An authorized non-owner channel sender with channel command access can approve or deny a pending permission request intended for the owner, causing the requested action to proceed without owner consent. The practical impact depends on the pending action and the host capabilities requested by the Claude Code run. The issue is fixed in version 2026.7.1."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "NETWORK",
            "baseScore": 8.6,
            "baseSeverity": "HIGH",
            "privilegesRequired": "LOW",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "PASSIVE",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "HIGH",
            "vulnIntegrityImpact": "HIGH"
          },
          "format": "CVSS"
        },
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 8,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:H",
            "version": "3.1"
          },
          "format": "CVSS"
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-862",
              "description": "Missing Authorization",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-09-26T02:19:09.595Z",
        "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "shortName": "VulnCheck"
      },
      "references": [
        {
          "name": "GitHub Security Advisory (GHSA-p5g8-m35v-7m82)",
          "tags": [
            "vendor-advisory"
          ],
          "url": "https://github.com/openclaw/openclaw/security/advisories/GHSA-p5g8-m35v-7m82"
        },
        {
          "name": "VulnCheck Advisory: OpenClaw before 2026.7.1 Authentication Bypass via MCP Channel",
          "tags": [
            "third-party-advisory"
          ],
          "url": "https://www.vulncheck.com/advisories/openclaw-before-2026.7.1-authentication-bypass-via-mcp-channel"
        }
      ],
      "title": "OpenClaw before 2026.7.1 Authentication Bypass via MCP Channel",
      "x_generator": {
        "engine": "vulncheck-endgame"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
    "assignerShortName": "VulnCheck",
    "cveId": "CVE-2026-100585",
    "datePublished": "2026-09-26T02:19:09.595Z",
    "dateReserved": "2026-09-26T01:03:42.741Z",
    "dateUpdated": "2026-09-26T02:19:09.595Z",
    "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-87G7-76GR-73G8

CVE-2026-100585 (GCVE-0-2026-100585)

Tags

Sightings

Nomenclature

Related by attack behaviour