CVE-2026-35021 (GCVE-0-2026-35021)

Vulnerability from cvelistv5 – Published: 2026-04-06 18:59 – Updated: 2026-04-13 20:07 Disputed
VLAI?
Title
Anthropic Claude Code & Agent SDK OS Command Injection via promptEditor.ts
Summary
Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection vulnerability in the prompt editor invocation utility that allows attackers to execute arbitrary commands by crafting malicious file paths. Attackers can inject shell metacharacters such as $() or backtick expressions into file paths that are interpolated into shell commands executed via execSync. Although the file path is wrapped in double quotes, POSIX shell semantics (POSIX §2.2.3) do not prevent command substitution within double quotes, allowing injected expressions to be evaluated and resulting in arbitrary command execution with the privileges of the user running the CLI.
Severity ?
8.4 (High)
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
7.8 (High)
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
CWE
  • CWE-78 - Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
Assigner
References
Impacted products
Vendor Product Version
Anthropic Claude Code Affected: 0 , ≤ 2.1.91 (semver)
Create a notification for this product.
Credits
Francesco Cipollone
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-35021",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-04-07T15:07:23.617111Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-04-07T15:10:32.217Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "defaultStatus": "unknown",
          "product": "Claude Code",
          "repo": "https://github.com/anthropics/claude-code",
          "vendor": "Anthropic",
          "versions": [
            {
              "lessThanOrEqual": "2.1.91",
              "status": "affected",
              "version": "0",
              "versionType": "semver"
            }
          ]
        },
        {
          "defaultStatus": "unknown",
          "product": "Claude Agent SDK for Python",
          "repo": "https://github.com/anthropics/claude-agent-sdk-python",
          "vendor": "Anthropic",
          "versions": [
            {
              "lessThanOrEqual": "0.1.55",
              "status": "affected",
              "version": "0",
              "versionType": "semver"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "finder",
          "value": "Francesco Cipollone"
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "supportingMedia": [
            {
              "base64": false,
              "type": "text/html",
              "value": "Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection vulnerability in the prompt editor invocation utility that allows attackers to execute arbitrary commands by crafting malicious file paths. Attackers can inject shell metacharacters such as $() or backtick expressions into file paths that are interpolated into shell commands executed via execSync. Although the file path is wrapped in double quotes, POSIX shell semantics (POSIX \u00a72.2.3) do not prevent command substitution within double quotes, allowing injected expressions to be evaluated and resulting in arbitrary command execution with the privileges of the user running the CLI.\u003cbr\u003e"
            }
          ],
          "value": "Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection vulnerability in the prompt editor invocation utility that allows attackers to execute arbitrary commands by crafting malicious file paths. Attackers can inject shell metacharacters such as $() or backtick expressions into file paths that are interpolated into shell commands executed via execSync. Although the file path is wrapped in double quotes, POSIX shell semantics (POSIX \u00a72.2.3) do not prevent command substitution within double quotes, allowing injected expressions to be evaluated and resulting in arbitrary command execution with the privileges of the user running the CLI."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "Automatable": "NOT_DEFINED",
            "Recovery": "NOT_DEFINED",
            "Safety": "NOT_DEFINED",
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "LOCAL",
            "baseScore": 8.4,
            "baseSeverity": "HIGH",
            "exploitMaturity": "NOT_DEFINED",
            "privilegesRequired": "NONE",
            "providerUrgency": "NOT_DEFINED",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "ACTIVE",
            "valueDensity": "NOT_DEFINED",
            "vectorString": "CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "HIGH",
            "vulnIntegrityImpact": "HIGH",
            "vulnerabilityResponseEffort": "NOT_DEFINED"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        },
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "LOCAL",
            "availabilityImpact": "HIGH",
            "baseScore": 7.8,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
            "version": "3.1"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        }
      ],
      "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": "2026-04-13T20:07:21.591Z",
        "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "shortName": "VulnCheck"
      },
      "references": [
        {
          "tags": [
            "technical-description",
            "exploit"
          ],
          "url": "https://phoenix.security/critical-ci-cd-nightmare-3-command-injection-flaws-in-claude-code-cli-allow-credential-exfiltration/"
        },
        {
          "tags": [
            "third-party-advisory"
          ],
          "url": "https://www.vulncheck.com/advisories/anthropic-claude-code-agent-sdk-os-command-injection-via-prompteditor-ts"
        }
      ],
      "source": {
        "discovery": "EXTERNAL"
      },
      "tags": [
        "disputed"
      ],
      "title": "Anthropic Claude Code \u0026 Agent SDK OS Command Injection via promptEditor.ts",
      "x_generator": {
        "engine": "Vulnogram 1.0.1"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
    "assignerShortName": "VulnCheck",
    "cveId": "CVE-2026-35021",
    "datePublished": "2026-04-06T18:59:06.979Z",
    "dateReserved": "2026-03-31T20:40:15.618Z",
    "dateUpdated": "2026-04-13T20:07:21.591Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-35021",
      "date": "2026-04-20",
      "epss": "0.00033",
      "percentile": "0.09551"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-35021\",\"sourceIdentifier\":\"disclosure@vulncheck.com\",\"published\":\"2026-04-06T20:16:25.067\",\"lastModified\":\"2026-04-13T20:16:34.557\",\"vulnStatus\":\"Undergoing Analysis\",\"cveTags\":[{\"sourceIdentifier\":\"disclosure@vulncheck.com\",\"tags\":[\"disputed\"]}],\"descriptions\":[{\"lang\":\"en\",\"value\":\"Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection vulnerability in the prompt editor invocation utility that allows attackers to execute arbitrary commands by crafting malicious file paths. Attackers can inject shell metacharacters such as $() or backtick expressions into file paths that are interpolated into shell commands executed via execSync. Although the file path is wrapped in double quotes, POSIX shell semantics (POSIX \u00a72.2.3) do not prevent command substitution within double quotes, allowing injected expressions to be evaluated and resulting in arbitrary command execution with the privileges of the user running the CLI.\"}],\"metrics\":{\"cvssMetricV40\":[{\"source\":\"disclosure@vulncheck.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"4.0\",\"vectorString\":\"CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/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\",\"baseScore\":8.4,\"baseSeverity\":\"HIGH\",\"attackVector\":\"LOCAL\",\"attackComplexity\":\"LOW\",\"attackRequirements\":\"NONE\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"ACTIVE\",\"vulnConfidentialityImpact\":\"HIGH\",\"vulnIntegrityImpact\":\"HIGH\",\"vulnAvailabilityImpact\":\"HIGH\",\"subConfidentialityImpact\":\"NONE\",\"subIntegrityImpact\":\"NONE\",\"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\"}}],\"cvssMetricV31\":[{\"source\":\"disclosure@vulncheck.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H\",\"baseScore\":7.8,\"baseSeverity\":\"HIGH\",\"attackVector\":\"LOCAL\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"REQUIRED\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":1.8,\"impactScore\":5.9}]},\"weaknesses\":[{\"source\":\"disclosure@vulncheck.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-78\"}]}],\"references\":[{\"url\":\"https://phoenix.security/critical-ci-cd-nightmare-3-command-injection-flaws-in-claude-code-cli-allow-credential-exfiltration/\",\"source\":\"disclosure@vulncheck.com\"},{\"url\":\"https://www.vulncheck.com/advisories/anthropic-claude-code-agent-sdk-os-command-injection-via-prompteditor-ts\",\"source\":\"disclosure@vulncheck.com\"}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-35021\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-04-07T15:07:23.617111Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-04-07T15:07:28.303Z\"}}], \"cna\": {\"tags\": [\"disputed\"], \"title\": \"Anthropic Claude Code \u0026 Agent SDK OS Command Injection via promptEditor.ts\", \"source\": {\"discovery\": \"EXTERNAL\"}, \"credits\": [{\"lang\": \"en\", \"type\": \"finder\", \"value\": \"Francesco Cipollone\"}], \"metrics\": [{\"format\": \"CVSS\", \"cvssV4_0\": {\"Safety\": \"NOT_DEFINED\", \"version\": \"4.0\", \"Recovery\": \"NOT_DEFINED\", \"baseScore\": 8.4, \"Automatable\": \"NOT_DEFINED\", \"attackVector\": \"LOCAL\", \"baseSeverity\": \"HIGH\", \"valueDensity\": \"NOT_DEFINED\", \"vectorString\": \"CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N\", \"exploitMaturity\": \"NOT_DEFINED\", \"providerUrgency\": \"NOT_DEFINED\", \"userInteraction\": \"ACTIVE\", \"attackComplexity\": \"LOW\", \"attackRequirements\": \"NONE\", \"privilegesRequired\": \"NONE\", \"subIntegrityImpact\": \"NONE\", \"vulnIntegrityImpact\": \"HIGH\", \"subAvailabilityImpact\": \"NONE\", \"vulnAvailabilityImpact\": \"HIGH\", \"subConfidentialityImpact\": \"NONE\", \"vulnConfidentialityImpact\": \"HIGH\", \"vulnerabilityResponseEffort\": \"NOT_DEFINED\"}, \"scenarios\": [{\"lang\": \"en\", \"value\": \"GENERAL\"}]}, {\"format\": \"CVSS\", \"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 7.8, \"attackVector\": \"LOCAL\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"REQUIRED\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"HIGH\"}, \"scenarios\": [{\"lang\": \"en\", \"value\": \"GENERAL\"}]}], \"affected\": [{\"repo\": \"https://github.com/anthropics/claude-code\", \"vendor\": \"Anthropic\", \"product\": \"Claude Code\", \"versions\": [{\"status\": \"affected\", \"version\": \"0\", \"versionType\": \"semver\", \"lessThanOrEqual\": \"2.1.91\"}], \"defaultStatus\": \"unknown\"}, {\"repo\": \"https://github.com/anthropics/claude-agent-sdk-python\", \"vendor\": \"Anthropic\", \"product\": \"Claude Agent SDK for Python\", \"versions\": [{\"status\": \"affected\", \"version\": \"0\", \"versionType\": \"semver\", \"lessThanOrEqual\": \"0.1.55\"}], \"defaultStatus\": \"unknown\"}], \"references\": [{\"url\": \"https://phoenix.security/critical-ci-cd-nightmare-3-command-injection-flaws-in-claude-code-cli-allow-credential-exfiltration/\", \"tags\": [\"technical-description\", \"exploit\"]}, {\"url\": \"https://www.vulncheck.com/advisories/anthropic-claude-code-agent-sdk-os-command-injection-via-prompteditor-ts\", \"tags\": [\"third-party-advisory\"]}], \"x_generator\": {\"engine\": \"Vulnogram 1.0.1\"}, \"descriptions\": [{\"lang\": \"en\", \"value\": \"Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection vulnerability in the prompt editor invocation utility that allows attackers to execute arbitrary commands by crafting malicious file paths. Attackers can inject shell metacharacters such as $() or backtick expressions into file paths that are interpolated into shell commands executed via execSync. Although the file path is wrapped in double quotes, POSIX shell semantics (POSIX \\u00a72.2.3) do not prevent command substitution within double quotes, allowing injected expressions to be evaluated and resulting in arbitrary command execution with the privileges of the user running the CLI.\", \"supportingMedia\": [{\"type\": \"text/html\", \"value\": \"Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection vulnerability in the prompt editor invocation utility that allows attackers to execute arbitrary commands by crafting malicious file paths. Attackers can inject shell metacharacters such as $() or backtick expressions into file paths that are interpolated into shell commands executed via execSync. Although the file path is wrapped in double quotes, POSIX shell semantics (POSIX \\u00a72.2.3) do not prevent command substitution within double quotes, allowing injected expressions to be evaluated and resulting in arbitrary command execution with the privileges of the user running the CLI.\u003cbr\u003e\", \"base64\": false}]}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-78\", \"description\": \"CWE-78 Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027)\"}]}], \"providerMetadata\": {\"orgId\": \"83251b91-4cc7-4094-a5c7-464a1b83ea10\", \"shortName\": \"VulnCheck\", \"dateUpdated\": \"2026-04-13T20:07:21.591Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-35021\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-04-13T20:07:21.591Z\", \"dateReserved\": \"2026-03-31T20:40:15.618Z\", \"assignerOrgId\": \"83251b91-4cc7-4094-a5c7-464a1b83ea10\", \"datePublished\": \"2026-04-06T18:59:06.979Z\", \"assignerShortName\": \"VulnCheck\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




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.