CVE-2026-55607 (GCVE-0-2026-55607)

Vulnerability from cvelistv5 – Published: 2026-06-29 14:04 – Updated: 2026-06-29 15:51
VLAI
Title
Claude Code: Sandbox Escape via Git Worktree Path Confusion Allows Unsandboxed Code Execution
Summary
Claude Code is an agentic coding tool. From 2.1.38 until 2.1.163, Claude Code's worktree handling allowed creation of worktrees named ".git" and navigation to worktrees outside the sandbox context, enabling git directory confusion attacks. By exploiting symlink manipulation and git fsmonitor execution during worktree operations, an attacker could overwrite files in the user's home directory (such as .zshenv), leading to code execution outside of seatbelt sandbox restrictions. Reliably exploiting this required the user to clone a malicious repository containing prompt injection content and run Claude Code against it. This vulnerability is fixed in 2.1.163.
Severity
7.7 (High)
CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
SSVC
Exploitation: none Automatable: no Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-06-29 15:51 UTC
CWE
  • CWE-22 - Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')
  • CWE-59 - Improper Link Resolution Before File Access ('Link Following')
  • CWE-78 - Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
Assigner
GitHub_M CNA under the mitre root
CNA scorecard C 72/100 over 7831 records in the last 180 days details
References
Impacted products
Vendor Product Version CPE status
anthropics claude-code Affected: >= 2.1.38, < 2.1.163
guessed Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-55607",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-06-29T15:51:20.888452Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-06-29T15:51:30.130Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "claude-code",
          "vendor": "anthropics",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 2.1.38, \u003c 2.1.163"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "Claude Code is an agentic coding tool.  From 2.1.38 until 2.1.163, Claude Code\u0027s worktree handling allowed creation of worktrees named \".git\" and navigation to worktrees outside the sandbox context, enabling git directory confusion attacks. By exploiting symlink manipulation and git fsmonitor execution during worktree operations, an attacker could overwrite files in the user\u0027s home directory (such as .zshenv), leading to code execution outside of seatbelt sandbox restrictions. Reliably exploiting this required the user to clone a malicious repository containing prompt injection content and run Claude Code against it. This vulnerability is fixed in 2.1.163."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "LOW",
            "attackRequirements": "PRESENT",
            "attackVector": "NETWORK",
            "baseScore": 7.7,
            "baseSeverity": "HIGH",
            "privilegesRequired": "NONE",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "PASSIVE",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "HIGH",
            "vulnIntegrityImpact": "HIGH"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-22",
              "description": "CWE-22: Improper Limitation of a Pathname to a Restricted Directory (\u0027Path Traversal\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-59",
              "description": "CWE-59: Improper Link Resolution Before File Access (\u0027Link Following\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "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": "2026-06-29T14:04:00.693Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/anthropics/claude-code/security/advisories/GHSA-7835-87q9-rgvv",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/anthropics/claude-code/security/advisories/GHSA-7835-87q9-rgvv"
        }
      ],
      "source": {
        "advisory": "GHSA-7835-87q9-rgvv",
        "discovery": "UNKNOWN"
      },
      "title": "Claude Code: Sandbox Escape via Git Worktree Path Confusion Allows Unsandboxed Code Execution"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-55607",
    "datePublished": "2026-06-29T14:04:00.693Z",
    "dateReserved": "2026-06-16T23:31:22.445Z",
    "dateUpdated": "2026-06-29T15:51:30.130Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-55607",
      "date": "2026-11-13",
      "epss": "0.00687",
      "percentile": "0.53249"
    },
    "nvd": {
      "cve": {
        "affected": [
          {
            "affectedData": [
              {
                "product": "claude-code",
                "vendor": "anthropics",
                "versions": [
                  {
                    "status": "affected",
                    "version": "\u003e= 2.1.38, \u003c 2.1.163"
                  }
                ]
              }
            ],
            "source": "security-advisories@github.com"
          }
        ],
        "configurations": [
          {
            "nodes": [
              {
                "cpeMatch": [
                  {
                    "criteria": "cpe:2.3:a:anthropic:claude_code:*:*:*:*:*:node.js:*:*",
                    "matchCriteriaId": "52A3407D-AEAF-40D4-8C07-9FE2B90E51FA",
                    "versionEndExcluding": "2.1.163",
                    "versionStartIncluding": "2.1.38",
                    "vulnerable": true
                  }
                ],
                "negate": false,
                "operator": "OR"
              }
            ]
          }
        ],
        "cveTags": [],
        "descriptions": [
          {
            "lang": "en",
            "value": "Claude Code is an agentic coding tool.  From 2.1.38 until 2.1.163, Claude Code\u0027s worktree handling allowed creation of worktrees named \".git\" and navigation to worktrees outside the sandbox context, enabling git directory confusion attacks. By exploiting symlink manipulation and git fsmonitor execution during worktree operations, an attacker could overwrite files in the user\u0027s home directory (such as .zshenv), leading to code execution outside of seatbelt sandbox restrictions. Reliably exploiting this required the user to clone a malicious repository containing prompt injection content and run Claude Code against it. This vulnerability is fixed in 2.1.163."
          },
          {
            "lang": "es",
            "value": "Claude Code es una herramienta de codificaci\u00f3n ag\u00e9ntica. Desde 2.1.38 hasta 2.1.163, el manejo de worktrees de Claude Code permit\u00eda la creaci\u00f3n de worktrees llamados \u2019.git\u2019 y la navegaci\u00f3n a worktrees fuera del contexto de la sandbox, habilitando ataques de confusi\u00f3n de directorio git. Al explotar la manipulaci\u00f3n de symlinks y la ejecuci\u00f3n de git fsmonitor durante las operaciones de worktree, un atacante podr\u00eda sobrescribir archivos en el directorio de inicio del usuario (como .zshenv), lo que llevaba a la ejecuci\u00f3n de c\u00f3digo fuera de las restricciones de la sandbox de seatbelt. Explotar esto de forma fiable requer\u00eda que el usuario clonara un repositorio malicioso que contuviera contenido de inyecci\u00f3n de prompts y ejecutara Claude Code contra \u00e9l. Esta vulnerabilidad est\u00e1 corregida en 2.1.163."
          }
        ],
        "id": "CVE-2026-55607",
        "lastModified": "2026-10-25T21:10:00.770",
        "metrics": {
          "cvssMetricV31": [
            {
              "cvssData": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 8.8,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "REQUIRED",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
                "version": "3.1"
              },
              "exploitabilityScore": 2.8,
              "impactScore": 5.9,
              "source": "nvd@nist.gov",
              "type": "Primary"
            }
          ],
          "cvssMetricV40": [
            {
              "cvssData": {
                "Automatable": "NOT_DEFINED",
                "Recovery": "NOT_DEFINED",
                "Safety": "NOT_DEFINED",
                "attackComplexity": "LOW",
                "attackRequirements": "PRESENT",
                "attackVector": "NETWORK",
                "availabilityRequirement": "NOT_DEFINED",
                "baseScore": 7.7,
                "baseSeverity": "HIGH",
                "confidentialityRequirement": "NOT_DEFINED",
                "exploitMaturity": "NOT_DEFINED",
                "integrityRequirement": "NOT_DEFINED",
                "modifiedAttackComplexity": "NOT_DEFINED",
                "modifiedAttackRequirements": "NOT_DEFINED",
                "modifiedAttackVector": "NOT_DEFINED",
                "modifiedPrivilegesRequired": "NOT_DEFINED",
                "modifiedSubAvailabilityImpact": "NOT_DEFINED",
                "modifiedSubConfidentialityImpact": "NOT_DEFINED",
                "modifiedSubIntegrityImpact": "NOT_DEFINED",
                "modifiedUserInteraction": "NOT_DEFINED",
                "modifiedVulnAvailabilityImpact": "NOT_DEFINED",
                "modifiedVulnConfidentialityImpact": "NOT_DEFINED",
                "modifiedVulnIntegrityImpact": "NOT_DEFINED",
                "privilegesRequired": "NONE",
                "providerUrgency": "NOT_DEFINED",
                "subAvailabilityImpact": "NONE",
                "subConfidentialityImpact": "NONE",
                "subIntegrityImpact": "NONE",
                "userInteraction": "PASSIVE",
                "valueDensity": "NOT_DEFINED",
                "vectorString": "CVSS:4.0/AV:N/AC:L/AT:P/PR:N/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",
                "version": "4.0",
                "vulnAvailabilityImpact": "HIGH",
                "vulnConfidentialityImpact": "HIGH",
                "vulnIntegrityImpact": "HIGH",
                "vulnerabilityResponseEffort": "NOT_DEFINED"
              },
              "source": "security-advisories@github.com",
              "type": "Secondary"
            }
          ],
          "ssvcV203": [
            {
              "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "ssvcData": {
                "id": "CVE-2026-55607",
                "options": [
                  {
                    "exploitation": "none"
                  },
                  {
                    "automatable": "no"
                  },
                  {
                    "technicalImpact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-06-29T15:51:20.888452Z",
                "version": "2.0.3"
              }
            }
          ]
        },
        "published": "2026-06-29T15:16:41.597",
        "references": [
          {
            "source": "security-advisories@github.com",
            "tags": [
              "Vendor Advisory"
            ],
            "url": "https://github.com/anthropics/claude-code/security/advisories/GHSA-7835-87q9-rgvv"
          }
        ],
        "sourceIdentifier": "security-advisories@github.com",
        "vulnStatus": "Analyzed",
        "weaknesses": [
          {
            "description": [
              {
                "lang": "en",
                "value": "CWE-22"
              },
              {
                "lang": "en",
                "value": "CWE-59"
              },
              {
                "lang": "en",
                "value": "CWE-78"
              }
            ],
            "source": "security-advisories@github.com",
            "type": "Secondary"
          }
        ]
      }
    },
    "redhat_vex": {
      "aggregate_severity": "Important",
      "current_release_date": "2026-10-15T11:04:51+00:00",
      "cve": "CVE-2026-55607",
      "id": "CVE-2026-55607",
      "initial_release_date": "2026-06-29T14:04:00.693000+00:00",
      "product_status:known_affected": "1",
      "source": "Red Hat CSAF VEX",
      "status": "final",
      "title": "Claude Code: @anthropic-ai/claude-code: Claude Code: Arbitrary code execution through git directory confusion",
      "url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-55607.json",
      "version": "3"
    },
    "vulnrichment": {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-55607",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-06-29T15:51:20.888452Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-06-29T15:51:26.139Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "claude-code",
              "vendor": "anthropics",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 2.1.38, \u003c 2.1.163"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "Claude Code is an agentic coding tool.  From 2.1.38 until 2.1.163, Claude Code\u0027s worktree handling allowed creation of worktrees named \".git\" and navigation to worktrees outside the sandbox context, enabling git directory confusion attacks. By exploiting symlink manipulation and git fsmonitor execution during worktree operations, an attacker could overwrite files in the user\u0027s home directory (such as .zshenv), leading to code execution outside of seatbelt sandbox restrictions. Reliably exploiting this required the user to clone a malicious repository containing prompt injection content and run Claude Code against it. This vulnerability is fixed in 2.1.163."
            }
          ],
          "metrics": [
            {
              "cvssV4_0": {
                "attackComplexity": "LOW",
                "attackRequirements": "PRESENT",
                "attackVector": "NETWORK",
                "baseScore": 7.7,
                "baseSeverity": "HIGH",
                "privilegesRequired": "NONE",
                "subAvailabilityImpact": "NONE",
                "subConfidentialityImpact": "NONE",
                "subIntegrityImpact": "NONE",
                "userInteraction": "PASSIVE",
                "vectorString": "CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
                "version": "4.0",
                "vulnAvailabilityImpact": "HIGH",
                "vulnConfidentialityImpact": "HIGH",
                "vulnIntegrityImpact": "HIGH"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-22",
                  "description": "CWE-22: Improper Limitation of a Pathname to a Restricted Directory (\u0027Path Traversal\u0027)",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-59",
                  "description": "CWE-59: Improper Link Resolution Before File Access (\u0027Link Following\u0027)",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "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": "2026-06-29T14:04:00.693Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/anthropics/claude-code/security/advisories/GHSA-7835-87q9-rgvv",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/anthropics/claude-code/security/advisories/GHSA-7835-87q9-rgvv"
            }
          ],
          "source": {
            "advisory": "GHSA-7835-87q9-rgvv",
            "discovery": "UNKNOWN"
          },
          "title": "Claude Code: Sandbox Escape via Git Worktree Path Confusion Allows Unsandboxed Code Execution"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-55607",
        "datePublished": "2026-06-29T14:04:00.693Z",
        "dateReserved": "2026-06-16T23:31:22.445Z",
        "dateUpdated": "2026-06-29T15:51:30.130Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.

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.
Vulnerability timeline

Sightings and recorded dates, grouped by day · UTC

JSON
How durations are calculated

Following the VTEM framework (Black Hat USA 2015), time to patch starts when the vendor or a coordinator was informed, total time to patch at discovery, and disclosure to patch at public disclosure; vendor response time runs from the report to its acknowledgement. Time to exploit and time unpatched start at the earliest discovery or report, falling back to public disclosure. Unpatched time ends at the first recorded patch, or the calculation time when no patch is recorded. Exploitation to patch shows the interval between those two events; a published proof of concept is a public exploit, not exploitation.

Each result shows its source dates. A negative interval means the end event came first; when date-only inputs leave the order open, the result says so. Date-only inputs are approximate. The earliest evidence wins: KEV report dates and sightings are labelled as such. Records describing another vulnerability are listed but never calculated from, and a PoC alone does not establish exploitation. Missing patch evidence does not prove that no patch exists. Filters below change the event list only.

Loading timeline…




    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.