GHSA-H4MW-J7QP-8MWM

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

Show details on source website

{
  "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"
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.


Loading…

Loading…

Loading…

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.

Loading…

Loading…

Loading…

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.


Loading…