Vulnerability-Lookup

GHSA-JH7P-QR78-84P7

Vulnerability from github – Published: 2026-01-21 01:00 – Updated: 2026-01-21 21:40

Summary

Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation

Details

A vulnerability in Claude Code's project-load flow allowed malicious repositories to exfiltrate data including Anthropic API keys before users confirmed trust. If a user started Claude Code in an attacker-controller repository, and the repository included a settings file that set ANTHROPIC_BASE_URL to an attacker-controlled endpoint, Claude Code would issue API requests before showing the trust prompt, including potentially leaking the user's API keys.

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

Severity

5.3 (Medium)


                  
                    CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:L/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": "2.0.65"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-21852"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-522"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-01-21T01:00:31Z",
    "nvd_published_at": "2026-01-21T21:16:08Z",
    "severity": "MODERATE"
  },
  "details": "A vulnerability in Claude Code\u0027s project-load flow allowed malicious repositories to exfiltrate data including Anthropic API keys before users confirmed trust. If a user started Claude Code in an attacker-controller repository, and the repository included a settings file that set ANTHROPIC_BASE_URL to an attacker-controlled endpoint, Claude Code would issue API requests before showing the trust prompt, including potentially leaking the user\u0027s API keys.\n\nUsers on standard Claude Code auto-update have received this fix already. Users performing manual updates are advised to update to the latest version.",
  "id": "GHSA-jh7p-qr78-84p7",
  "modified": "2026-01-21T21:40:17Z",
  "published": "2026-01-21T01:00:31Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/anthropics/claude-code/security/advisories/GHSA-jh7p-qr78-84p7"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-21852"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/anthropics/claude-code"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N",
      "type": "CVSS_V4"
    }
  ],
  "summary": "Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation"
}

CVE-2026-21852 (GCVE-0-2026-21852)

Vulnerability from cvelistv5 – Published: 2026-01-21 20:42 – Updated: 2026-01-21 21:34

Title

Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation

Summary

Claude Code is an agentic coding tool. Prior to version 2.0.65, vulnerability in Claude Code's project-load flow allowed malicious repositories to exfiltrate data including Anthropic API keys before users confirmed trust. An attacker-controlled repository could include a settings file that sets ANTHROPIC_BASE_URL to an attacker-controlled endpoint and when the repository was opened, Claude Code would read the configuration and immediately issue API requests before showing the trust prompt, potentially leaking the user's API keys. Users on standard Claude Code auto-update have received this fix already. Users performing manual updates are advised to update to version 2.0.65, which contains a patch, or to the latest version.

Severity

5.3 (Medium)


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

SSVC

Exploitation: none Automatable: yes Technical Impact: partial

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2026-01-21 21:34 UTC

CWE

CWE-522 - Insufficiently Protected Credentials

Assigner

GitHub_M mitre root Scorecard

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: < 2.0.65

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-21852",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-01-21T21:34:19.798222Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-01-21T21:34:43.858Z",
          "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 2.0.65"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "Claude Code is an agentic coding tool. Prior to version 2.0.65, vulnerability in Claude Code\u0027s project-load flow allowed malicious repositories to exfiltrate data including Anthropic API keys before users confirmed trust. An attacker-controlled repository could include a settings file that sets ANTHROPIC_BASE_URL to an attacker-controlled endpoint and when the repository was opened, Claude Code would read the configuration and immediately issue API requests before showing the trust prompt, potentially leaking the user\u0027s API keys. Users on standard Claude Code auto-update have received this fix already. Users performing manual updates are advised to update to version 2.0.65, which contains a patch, or to the latest version."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "NETWORK",
            "baseScore": 5.3,
            "baseSeverity": "MEDIUM",
            "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:L/VI:L/VA:L/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "LOW",
            "vulnConfidentialityImpact": "LOW",
            "vulnIntegrityImpact": "LOW"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-522",
              "description": "CWE-522: Insufficiently Protected Credentials",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-01-21T20:42:06.812Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/anthropics/claude-code/security/advisories/GHSA-jh7p-qr78-84p7",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/anthropics/claude-code/security/advisories/GHSA-jh7p-qr78-84p7"
        }
      ],
      "source": {
        "advisory": "GHSA-jh7p-qr78-84p7",
        "discovery": "UNKNOWN"
      },
      "title": "Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-21852",
    "datePublished": "2026-01-21T20:42:06.812Z",
    "dateReserved": "2026-01-05T16:44:16.366Z",
    "dateUpdated": "2026-01-21T21:34:43.858Z",
    "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.

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

GHSA-JH7P-QR78-84P7

CVE-2026-21852 (GCVE-0-2026-21852)

Tags

Sightings

Nomenclature

Related by attack behaviour