Vulnerability-Lookup

CNVD-2026-13375

Vulnerability from cnvd - Published: 2026-03-12

Title

OpenClaw存在未明漏洞（CNVD-2026-13375）

Description

OpenClaw是OpenClaw开源的一个智能人工助理。 OpenClaw存在安全漏洞，该漏洞源于openclaw://agent深度链接的确认对话框仅显示消息的前240个字符，但执行完整消息，攻击者可利用该漏洞通过填充空格将恶意有效载荷推至可见预览之外，增加用户批准与实际执行不同消息的风险，导致任意命令执行。

Severity

高

Patch Name

OpenClaw存在未明漏洞（CNVD-2026-13375）的补丁

Patch Description

Formal description

厂商已发布了漏洞修复程序，请及时关注更新： https://github.com/openclaw/openclaw/releases

Reference

https://github.com/openclaw/openclaw/commit/28d9dd7a772501ccc3f71457b4adfee79084fe6f

Impacted products

Name
OpenClaw OpenClaw >=2026.2.6，<=2026.2.13

Show details on source website

JSON

To clipboard

{
  "cves": {
    "cve": {
      "cveNumber": "CVE-2026-26320",
      "cveUrl": "https://nvd.nist.gov/vuln/detail/CVE-2026-26320"
    }
  },
  "description": "OpenClaw\u662fOpenClaw\u5f00\u6e90\u7684\u4e00\u4e2a\u667a\u80fd\u4eba\u5de5\u52a9\u7406\u3002\n\nOpenClaw\u5b58\u5728\u5b89\u5168\u6f0f\u6d1e\uff0c\u8be5\u6f0f\u6d1e\u6e90\u4e8eopenclaw://agent\u6df1\u5ea6\u94fe\u63a5\u7684\u786e\u8ba4\u5bf9\u8bdd\u6846\u4ec5\u663e\u793a\u6d88\u606f\u7684\u524d240\u4e2a\u5b57\u7b26\uff0c\u4f46\u6267\u884c\u5b8c\u6574\u6d88\u606f\uff0c\u653b\u51fb\u8005\u53ef\u5229\u7528\u8be5\u6f0f\u6d1e\u901a\u8fc7\u586b\u5145\u7a7a\u683c\u5c06\u6076\u610f\u6709\u6548\u8f7d\u8377\u63a8\u81f3\u53ef\u89c1\u9884\u89c8\u4e4b\u5916\uff0c\u589e\u52a0\u7528\u6237\u6279\u51c6\u4e0e\u5b9e\u9645\u6267\u884c\u4e0d\u540c\u6d88\u606f\u7684\u98ce\u9669\uff0c\u5bfc\u81f4\u4efb\u610f\u547d\u4ee4\u6267\u884c\u3002",
  "formalWay": "\u5382\u5546\u5df2\u53d1\u5e03\u4e86\u6f0f\u6d1e\u4fee\u590d\u7a0b\u5e8f\uff0c\u8bf7\u53ca\u65f6\u5173\u6ce8\u66f4\u65b0\uff1a\r\nhttps://github.com/openclaw/openclaw/releases",
  "isEvent": "\u901a\u7528\u8f6f\u786c\u4ef6\u6f0f\u6d1e",
  "number": "CNVD-2026-13375",
  "openTime": "2026-03-12",
  "patchDescription": "OpenClaw\u662fOpenClaw\u5f00\u6e90\u7684\u4e00\u4e2a\u667a\u80fd\u4eba\u5de5\u52a9\u7406\u3002\r\n\r\nOpenClaw\u5b58\u5728\u5b89\u5168\u6f0f\u6d1e\uff0c\u8be5\u6f0f\u6d1e\u6e90\u4e8eopenclaw://agent\u6df1\u5ea6\u94fe\u63a5\u7684\u786e\u8ba4\u5bf9\u8bdd\u6846\u4ec5\u663e\u793a\u6d88\u606f\u7684\u524d240\u4e2a\u5b57\u7b26\uff0c\u4f46\u6267\u884c\u5b8c\u6574\u6d88\u606f\uff0c\u653b\u51fb\u8005\u53ef\u5229\u7528\u8be5\u6f0f\u6d1e\u901a\u8fc7\u586b\u5145\u7a7a\u683c\u5c06\u6076\u610f\u6709\u6548\u8f7d\u8377\u63a8\u81f3\u53ef\u89c1\u9884\u89c8\u4e4b\u5916\uff0c\u589e\u52a0\u7528\u6237\u6279\u51c6\u4e0e\u5b9e\u9645\u6267\u884c\u4e0d\u540c\u6d88\u606f\u7684\u98ce\u9669\uff0c\u5bfc\u81f4\u4efb\u610f\u547d\u4ee4\u6267\u884c\u3002\u76ee\u524d\uff0c\u4f9b\u5e94\u5546\u53d1\u5e03\u4e86\u5b89\u5168\u516c\u544a\u53ca\u76f8\u5173\u8865\u4e01\u4fe1\u606f\uff0c\u4fee\u590d\u4e86\u6b64\u6f0f\u6d1e\u3002",
  "patchName": "OpenClaw\u5b58\u5728\u672a\u660e\u6f0f\u6d1e\uff08CNVD-2026-13375\uff09\u7684\u8865\u4e01",
  "products": {
    "product": "OpenClaw OpenClaw \u003e=2026.2.6\uff0c\u003c=2026.2.13"
  },
  "referenceLink": "https://github.com/openclaw/openclaw/commit/28d9dd7a772501ccc3f71457b4adfee79084fe6f",
  "serverity": "\u9ad8",
  "submitTime": "2026-03-02",
  "title": "OpenClaw\u5b58\u5728\u672a\u660e\u6f0f\u6d1e\uff08CNVD-2026-13375\uff09"
}

CVE-2026-26320 (GCVE-0-2026-26320)

Vulnerability from cvelistv5 – Published: 2026-02-19 22:24 – Updated: 2026-02-20 15:41

Title

OpenClaw macOS deep link confirmation truncation can conceal executed agent message

Summary

OpenClaw is a personal AI assistant. OpenClaw macOS desktop client registers the `openclaw://` URL scheme. For `openclaw://agent` deep links without an unattended `key`, the app shows a confirmation dialog that previously displayed only the first 240 characters of the message, but executed the full message after the user clicked "Run." At the time of writing, the OpenClaw macOS desktop client is still in beta. In versions 2026.2.6 through 2026.2.13, an attacker could pad the message with whitespace to push a malicious payload outside the visible preview, increasing the chance a user approves a different message than the one that is actually executed. If a user runs the deep link, the agent may perform actions that can lead to arbitrary command execution depending on the user's configured tool approvals/allowlists. This is a social-engineering mediated vulnerability: the confirmation prompt could be made to misrepresent the executed message. The issue is fixed in 2026.2.14. Other mitigations include not approve unexpected "Run OpenClaw agent?" prompts triggered while browsing untrusted sites and usingunattended deep links only with a valid `key` for trusted personal automations.

Severity ?

7.1 (High)


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

CWE

CWE-451 - User Interface (UI) Misrepresentation of Critical Information

Assigner

GitHub_M

References

URL

Tags

	https://github.com/openclaw/openclaw/security/adv…	x_refsource_CONFIRM
	https://github.com/openclaw/openclaw/commit/28d9d…	x_refsource_MISC
	https://github.com/openclaw/openclaw/releases/tag…	x_refsource_MISC

Impacted products

	Vendor	Product	Version
	openclaw	openclaw	Affected: >= 2026.2.6-0, < 2026.2.14

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-26320",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-02-20T15:32:02.128548Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-02-20T15:41:16.051Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "openclaw",
          "vendor": "openclaw",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 2026.2.6-0, \u003c 2026.2.14"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "OpenClaw is a personal AI assistant. OpenClaw macOS desktop client registers the `openclaw://` URL scheme. For `openclaw://agent` deep links without an unattended `key`, the app shows a confirmation dialog that previously displayed only the first 240 characters of the message, but executed the full message after the user clicked \"Run.\" At the time of writing, the OpenClaw macOS desktop client is still in beta. In versions 2026.2.6 through 2026.2.13, an attacker could pad the message with whitespace to push a malicious payload outside the visible preview, increasing the chance a user approves a different message than the one that is actually executed. If a user runs the deep link, the agent may perform actions that can lead to arbitrary command execution depending on the user\u0027s configured tool approvals/allowlists. This is a social-engineering mediated vulnerability: the confirmation prompt could be made to misrepresent the executed message. The issue is fixed in 2026.2.14. Other mitigations include not approve unexpected \"Run OpenClaw agent?\" prompts triggered while browsing untrusted sites and usingunattended deep links only with a valid `key` for trusted personal automations."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "NETWORK",
            "baseScore": 7.1,
            "baseSeverity": "HIGH",
            "privilegesRequired": "NONE",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "PASSIVE",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:N/VI:H/VA:N/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "NONE",
            "vulnConfidentialityImpact": "NONE",
            "vulnIntegrityImpact": "HIGH"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-451",
              "description": "CWE-451: User Interface (UI) Misrepresentation of Critical Information",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-02-19T22:24:33.409Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/openclaw/openclaw/security/advisories/GHSA-7q2j-c4q5-rm27",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/openclaw/openclaw/security/advisories/GHSA-7q2j-c4q5-rm27"
        },
        {
          "name": "https://github.com/openclaw/openclaw/commit/28d9dd7a772501ccc3f71457b4adfee79084fe6f",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/openclaw/openclaw/commit/28d9dd7a772501ccc3f71457b4adfee79084fe6f"
        },
        {
          "name": "https://github.com/openclaw/openclaw/releases/tag/v2026.2.14",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/openclaw/openclaw/releases/tag/v2026.2.14"
        }
      ],
      "source": {
        "advisory": "GHSA-7q2j-c4q5-rm27",
        "discovery": "UNKNOWN"
      },
      "title": "OpenClaw macOS deep link confirmation truncation can conceal executed agent message"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-26320",
    "datePublished": "2026-02-19T22:24:33.409Z",
    "dateReserved": "2026-02-13T16:27:51.808Z",
    "dateUpdated": "2026-02-20T15:41:16.051Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

Sightings

Author	Source	Type	Date

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.

Detection rules are retrieved from Rulezet.

Action not permitted

CNVD-2026-13375

CVE-2026-26320 (GCVE-0-2026-26320)

Tags

Sightings

Nomenclature