Vulnerability-Lookup

GHSA-H4MW-J7QP-8MWM

Vulnerability from github – Published: 2026-10-16 19:44 – Updated: 2026-10-16 19:44

Summary

Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution

Details

The Claude Agent SDK for Python passed the resume option to the Claude CLI without validation, allowing a value beginning with - to be interpreted as a separate CLI flag. An attacker who controlled the resume value could inject an --mcp-config flag defining a stdio MCP server, resulting in arbitrary command execution at CLI startup that bypassed the SDK's permission controls. Exploitation required an application to pass untrusted input as the session ID to resume.

Users are advised to update to the latest version of the claude-agent-sdk package.

Thank you to hackerone.com/moamenmahmood for reporting this issue.

Severity

9.2 (Critical)


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

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "claude-agent-sdk"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.2.121"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-96620"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-20",
      "CWE-78",
      "CWE-88"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-10-16T19:44:37Z",
    "nvd_published_at": null,
    "severity": "CRITICAL"
  },
  "details": "The Claude Agent SDK for Python passed the `resume` option to the Claude CLI without validation, allowing a value beginning with `-` to be interpreted as a separate CLI flag. An attacker who controlled the `resume` value could inject an `--mcp-config` flag defining a stdio MCP server, resulting in arbitrary command execution at CLI startup that bypassed the SDK\u0027s permission controls. Exploitation required an application to pass untrusted input as the session ID to resume.\n\nUsers are advised to update to the latest version of the claude-agent-sdk package.\n\nThank you to hackerone.com/moamenmahmood for reporting this issue.",
  "id": "GHSA-h4mw-j7qp-8mwm",
  "modified": "2026-10-16T19:44:37Z",
  "published": "2026-10-16T19:44:37Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/anthropics/claude-agent-sdk-python/security/advisories/GHSA-h4mw-j7qp-8mwm"
    },
    {
      "type": "WEB",
      "url": "https://github.com/anthropics/claude-agent-sdk-python/pull/1123"
    },
    {
      "type": "WEB",
      "url": "https://github.com/anthropics/claude-agent-sdk-python/commit/347a1cb88d7652199399db1b7f914e0a459a6662"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/anthropics/claude-agent-sdk-python"
    },
    {
      "type": "WEB",
      "url": "https://github.com/anthropics/claude-agent-sdk-python/releases/tag/v0.2.121"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
      "type": "CVSS_V4"
    }
  ],
  "summary": "Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution"
}

CVE-2026-96620 (GCVE-0-2026-96620)

Vulnerability from cvelistv5 – Published: 2026-10-16 19:44 – Updated: 2026-10-16 19:44

Title

Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution

Summary

Claude Agent SDK is a Python SDK for Claude Code. Prior to 0.2.121, the resume option is passed to the Claude CLI as a separate token without validation, so a dash-leading value is parsed as an independent CLI flag. An attacker can inject the --mcp-config flag to define a stdio MCP server, causing arbitrary command execution at CLI startup outside the SDK permission controls. The issue is exploitable when an application passes untrusted input as the session ID to resume. This issue is fixed in version 0.2.121.

Severity

9.2 (Critical)


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

CWE

CWE-20 - Improper Input Validation
CWE-78 - Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
CWE-88 - Improper Neutralization of Argument Delimiters in a Command ('Argument Injection')

Assigner

GitHub_M CNA under the mitre root

CNA scorecard C 72/100 over 7771 records in the last 180 days details

References

4 references

URL	Tags
https://github.com/anthropics/claude-agent-sdk-py…	x_refsource_CONFIRM
https://github.com/anthropics/claude-agent-sdk-py…	x_refsource_MISC
https://github.com/anthropics/claude-agent-sdk-py…	x_refsource_MISC
https://github.com/anthropics/claude-agent-sdk-py…	x_refsource_MISC

Impacted products

1 product

Vendor	Product	Version
anthropics	claude-agent-sdk-python	Affected: < 0.2.121

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "cna": {
      "affected": [
        {
          "product": "claude-agent-sdk-python",
          "vendor": "anthropics",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.2.121"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "Claude Agent SDK is a Python SDK for Claude Code. Prior to 0.2.121, the resume option is passed to the Claude CLI as a separate token without validation, so a dash-leading value is parsed as an independent CLI flag. An attacker can inject the --mcp-config flag to define a stdio MCP server, causing arbitrary command execution at CLI startup outside the SDK permission controls. The issue is exploitable when an application passes untrusted input as the session ID to resume. This issue is fixed in version 0.2.121."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "LOW",
            "attackRequirements": "PRESENT",
            "attackVector": "NETWORK",
            "baseScore": 9.2,
            "baseSeverity": "CRITICAL",
            "privilegesRequired": "NONE",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "NONE",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/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"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-88",
              "description": "CWE-88: Improper Neutralization of Argument Delimiters in a Command (\u0027Argument Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-10-16T19:44:01.260Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/anthropics/claude-agent-sdk-python/security/advisories/GHSA-h4mw-j7qp-8mwm",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/anthropics/claude-agent-sdk-python/security/advisories/GHSA-h4mw-j7qp-8mwm"
        },
        {
          "name": "https://github.com/anthropics/claude-agent-sdk-python/pull/1123",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/anthropics/claude-agent-sdk-python/pull/1123"
        },
        {
          "name": "https://github.com/anthropics/claude-agent-sdk-python/commit/347a1cb88d7652199399db1b7f914e0a459a6662",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/anthropics/claude-agent-sdk-python/commit/347a1cb88d7652199399db1b7f914e0a459a6662"
        },
        {
          "name": "https://github.com/anthropics/claude-agent-sdk-python/releases/tag/v0.2.121",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/anthropics/claude-agent-sdk-python/releases/tag/v0.2.121"
        }
      ],
      "source": {
        "advisory": "GHSA-h4mw-j7qp-8mwm",
        "discovery": "UNKNOWN"
      },
      "title": "Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-96620",
    "datePublished": "2026-10-16T19:44:01.260Z",
    "dateReserved": "2026-09-23T14:35:50.128Z",
    "dateUpdated": "2026-10-16T19:44:01.260Z",
    "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

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