Vulnerability-Lookup

GHSA-MHG7-666J-CQG4

Vulnerability from github – Published: 2026-02-06 19:04 – Updated: 2026-02-06 19:04

Summary

Claude Code Vulnerable to Command Injection via Piped sed Command Bypasses File Write Restrictions

Details

Claude Code failed to properly validate commands using piped sed operations with the echo command, allowing attackers to bypass file write restrictions. This vulnerability enabled writing to sensitive directories like the .claude folder and paths outside the project scope. Exploiting this required the ability to execute commands through Claude Code with the "accept edits" feature enabled.

Users on standard Claude Code auto-update received this fix automatically. Users performing manual updates are advised to update to the latest version.

Claude Code thanks hackerone.com/nil221 for reporting this issue!

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

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "npm",
        "name": "@anthropic-ai/claude-code"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "2.0.55"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-25723"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-20",
      "CWE-78"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-02-06T19:04:51Z",
    "nvd_published_at": "2026-02-06T18:15:59Z",
    "severity": "HIGH"
  },
  "details": "Claude Code failed to properly validate commands using piped sed operations with the echo command, allowing attackers to bypass file write restrictions. This vulnerability enabled writing to sensitive directories like the .claude folder and paths outside the project scope. Exploiting this required the ability to execute commands through Claude Code with the \"accept edits\" feature enabled. \n\nUsers on standard Claude Code auto-update received this fix automatically. Users performing manual updates are advised to update to the latest version.\n\nClaude Code thanks hackerone.com/nil221 for reporting this issue!",
  "id": "GHSA-mhg7-666j-cqg4",
  "modified": "2026-02-06T19:04:51Z",
  "published": "2026-02-06T19:04:51Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/anthropics/claude-code/security/advisories/GHSA-mhg7-666j-cqg4"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-25723"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/anthropics/claude-code"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "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",
      "type": "CVSS_V4"
    }
  ],
  "summary": "Claude Code Vulnerable to Command Injection via Piped sed Command Bypasses File Write Restrictions"
}

CVE-2026-25723 (GCVE-0-2026-25723)

Vulnerability from cvelistv5 – Published: 2026-02-06 17:52 – Updated: 2026-02-06 18:40

Title

Claude Code Vulnerable to Command Injection via Piped sed Command Bypasses File Write Restrictions

Summary

Claude Code is an agentic coding tool. Prior to version 2.0.55, Claude Code failed to properly validate commands using piped sed operations with the echo command, allowing attackers to bypass file write restrictions. This vulnerability enabled writing to sensitive directories like the .claude folder and paths outside the project scope. Exploiting this required the ability to execute commands through Claude Code with the "accept edits" feature enabled. This issue has been patched in version 2.0.55.

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 2026-02-06 18:40 UTC

CWE

CWE-20 - Improper Input Validation
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

1 reference

URL	Tags
https://github.com/anthropics/claude-code/securit…	x_refsource_CONFIRM

Impacted products

1 product

Vendor	Product	Version
anthropics	claude-code	Affected: < 2.0.55

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-25723",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-02-06T18:40:45.408037Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-02-06T18:40:54.158Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "claude-code",
          "vendor": "anthropics",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 2.0.55"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "Claude Code is an agentic coding tool. Prior to version 2.0.55, Claude Code failed to properly validate commands using piped sed operations with the echo command, allowing attackers to bypass file write restrictions. This vulnerability enabled writing to sensitive directories like the .claude folder and paths outside the project scope. Exploiting this required the ability to execute commands through Claude Code with the \"accept edits\" feature enabled. This issue has been patched in version 2.0.55."
        }
      ],
      "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-20",
              "description": "CWE-20: Improper Input Validation",
              "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": "2026-02-06T17:52:59.028Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/anthropics/claude-code/security/advisories/GHSA-mhg7-666j-cqg4",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/anthropics/claude-code/security/advisories/GHSA-mhg7-666j-cqg4"
        }
      ],
      "source": {
        "advisory": "GHSA-mhg7-666j-cqg4",
        "discovery": "UNKNOWN"
      },
      "title": "Claude Code Vulnerable to Command Injection via Piped sed Command Bypasses File Write Restrictions"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-25723",
    "datePublished": "2026-02-06T17:52:59.028Z",
    "dateReserved": "2026-02-05T16:48:00.426Z",
    "dateUpdated": "2026-02-06T18:40:54.158Z",
    "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.

Vulnerability timeline

Sightings and recorded dates, grouped by day · UTC

Order 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.

Publication & reservation Sightings KEV catalogs Other timestamps

Loading timeline…

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