CVE-2026-47751 (GCVE-0-2026-47751)

Vulnerability from cvelistv5 – Published: 2026-07-16 15:59 – Updated: 2026-07-16 15:59
VLAI
Title
Claude Code Action: Malicious MCP Server Configuration in PRs Enables Remote Code Execution and Secret Exfiltration
Summary
Claude Code Action is a general-purpose GitHub action that runs Claude Code on GitHub pull requests and issues. Prior to 1.0.74, because the action checked out attacker-controlled pull request head branches, read .mcp.json from the working directory via default setting sources, and unconditionally enabled all project MCP servers via enableAllProjectMcpServers, an attacker who opened a pull request containing a malicious .mcp.json file could achieve arbitrary code execution on the GitHub Actions runner and exfiltrate secrets available to the workflow (such as API keys and tokens) when a privileged user or an automatic trigger invoked the Claude action on the pull request. This issue is fixed in version 1.0.74, which restores .claude/ and .mcp.json from the pull request base branch before the CLI runs.
Severity
5.3 (Medium)
CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:L/VI:L/VA:N/SC:H/SI:H/SA:N
CWE
  • CWE-78 - Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
  • CWE-200 - Exposure of Sensitive Information to an Unauthorized Actor
Assigner
References
Impacted products
Show details on NVD website
To clipboard 

{
  "containers": {
    "cna": {
      "affected": [
        {
          "product": "claude-code-action",
          "vendor": "anthropics",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 1.0.74"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "Claude Code Action is a general-purpose GitHub action that runs Claude Code on GitHub pull requests and issues. Prior to 1.0.74, because the action checked out attacker-controlled pull request head branches, read .mcp.json from the working directory via default setting sources, and unconditionally enabled all project MCP servers via enableAllProjectMcpServers, an attacker who opened a pull request containing a malicious .mcp.json file could achieve arbitrary code execution on the GitHub Actions runner and exfiltrate secrets available to the workflow (such as API keys and tokens) when a privileged user or an automatic trigger invoked the Claude action on the pull request. This issue is fixed in version 1.0.74, which restores .claude/ and .mcp.json from the pull request base branch before the CLI runs."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "LOW",
            "attackRequirements": "PRESENT",
            "attackVector": "NETWORK",
            "baseScore": 5.3,
            "baseSeverity": "MEDIUM",
            "privilegesRequired": "LOW",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "HIGH",
            "subIntegrityImpact": "HIGH",
            "userInteraction": "NONE",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:L/VI:L/VA:N/SC:H/SI:H/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "NONE",
            "vulnConfidentialityImpact": "LOW",
            "vulnIntegrityImpact": "LOW"
          }
        }
      ],
      "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"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-200",
              "description": "CWE-200: Exposure of Sensitive Information to an Unauthorized Actor",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-07-16T15:59:29.885Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/anthropics/claude-code-action/security/advisories/GHSA-8q5r-mmjf-575q",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/anthropics/claude-code-action/security/advisories/GHSA-8q5r-mmjf-575q"
        },
        {
          "name": "https://github.com/anthropics/claude-code-action/pull/1066",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/anthropics/claude-code-action/pull/1066"
        },
        {
          "name": "https://github.com/anthropics/claude-code-action/commit/9ddce40de8c1ab71fb6303a125fdad0968dc1312",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/anthropics/claude-code-action/commit/9ddce40de8c1ab71fb6303a125fdad0968dc1312"
        },
        {
          "name": "https://github.com/anthropics/claude-code-action/releases/tag/v1.0.74",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/anthropics/claude-code-action/releases/tag/v1.0.74"
        }
      ],
      "source": {
        "advisory": "GHSA-8q5r-mmjf-575q",
        "discovery": "UNKNOWN"
      },
      "title": "Claude Code Action: Malicious MCP Server Configuration in PRs Enables Remote Code Execution and Secret Exfiltration"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-47751",
    "datePublished": "2026-07-16T15:59:29.885Z",
    "dateReserved": "2026-05-19T22:16:39.505Z",
    "dateUpdated": "2026-07-16T15:59:29.885Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-47751",
      "date": "2026-06-14",
      "epss": "0.00069",
      "percentile": "0.21608"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-47751\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-07-16T17:16:57.357\",\"lastModified\":\"2026-07-16T17:35:04.970\",\"vulnStatus\":\"Awaiting Analysis\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"Claude Code Action is a general-purpose GitHub action that runs Claude Code on GitHub pull requests and issues. Prior to 1.0.74, because the action checked out attacker-controlled pull request head branches, read .mcp.json from the working directory via default setting sources, and unconditionally enabled all project MCP servers via enableAllProjectMcpServers, an attacker who opened a pull request containing a malicious .mcp.json file could achieve arbitrary code execution on the GitHub Actions runner and exfiltrate secrets available to the workflow (such as API keys and tokens) when a privileged user or an automatic trigger invoked the Claude action on the pull request. This issue is fixed in version 1.0.74, which restores .claude/ and .mcp.json from the pull request base branch before the CLI runs.\"}],\"affected\":[{\"source\":\"security-advisories@github.com\",\"affectedData\":[{\"vendor\":\"anthropics\",\"product\":\"claude-code-action\",\"versions\":[{\"version\":\"\u003c 1.0.74\",\"status\":\"affected\"}]}]}],\"metrics\":{\"cvssMetricV40\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"4.0\",\"vectorString\":\"CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:L/VI:L/VA:N/SC:H/SI:H/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\",\"baseScore\":5.3,\"baseSeverity\":\"MEDIUM\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"attackRequirements\":\"PRESENT\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"vulnConfidentialityImpact\":\"LOW\",\"vulnIntegrityImpact\":\"LOW\",\"vulnAvailabilityImpact\":\"NONE\",\"subConfidentialityImpact\":\"HIGH\",\"subIntegrityImpact\":\"HIGH\",\"subAvailabilityImpact\":\"NONE\",\"exploitMaturity\":\"NOT_DEFINED\",\"confidentialityRequirement\":\"NOT_DEFINED\",\"integrityRequirement\":\"NOT_DEFINED\",\"availabilityRequirement\":\"NOT_DEFINED\",\"modifiedAttackVector\":\"NOT_DEFINED\",\"modifiedAttackComplexity\":\"NOT_DEFINED\",\"modifiedAttackRequirements\":\"NOT_DEFINED\",\"modifiedPrivilegesRequired\":\"NOT_DEFINED\",\"modifiedUserInteraction\":\"NOT_DEFINED\",\"modifiedVulnConfidentialityImpact\":\"NOT_DEFINED\",\"modifiedVulnIntegrityImpact\":\"NOT_DEFINED\",\"modifiedVulnAvailabilityImpact\":\"NOT_DEFINED\",\"modifiedSubConfidentialityImpact\":\"NOT_DEFINED\",\"modifiedSubIntegrityImpact\":\"NOT_DEFINED\",\"modifiedSubAvailabilityImpact\":\"NOT_DEFINED\",\"Safety\":\"NOT_DEFINED\",\"Automatable\":\"NOT_DEFINED\",\"Recovery\":\"NOT_DEFINED\",\"valueDensity\":\"NOT_DEFINED\",\"vulnerabilityResponseEffort\":\"NOT_DEFINED\",\"providerUrgency\":\"NOT_DEFINED\"}}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Primary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-78\"},{\"lang\":\"en\",\"value\":\"CWE-200\"}]}],\"references\":[{\"url\":\"https://github.com/anthropics/claude-code-action/commit/9ddce40de8c1ab71fb6303a125fdad0968dc1312\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/anthropics/claude-code-action/pull/1066\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/anthropics/claude-code-action/releases/tag/v1.0.74\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/anthropics/claude-code-action/security/advisories/GHSA-8q5r-mmjf-575q\",\"source\":\"security-advisories@github.com\"}]}}"
  }
}



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.


Detection rules are retrieved from Rulezet.