ZeroDay Findings
Sign inSign up

Findings

Vulnerability · CVE-2026-96620

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

Published Oct 16, 2026 · corrected/updated Oct 16, 2026 · evidence confidence high

The Claude Agent SDK for Python passed the 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 value could inject an 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.

Grounded briefings

Catalog interpretations for three audiences. Each brief cites ingested metadata and the original advisories below. They are not independent research and they do not invent exploit steps.

Executive

CVE-2026-96620 is a critical public vulnerability record for this product. It is not currently listed in the CISA Known Exploited catalog. Check the linked vendor or CERT advisories for patch status. This summary is a catalog interpretation of the ingested metadata and cites the original advisories below.

System administrator

Identify whether this product is in your estate, then compare installed versions with the affected ranges. Affected packages or ranges on record: claude-agent-sdk (0 → 0.2.121); claude-agent-sdk (< 0.2.121). Check the linked vendor or CERT advisories for patch status. Prefer the vendor or distribution advisory linked in Sources before changing production systems. This is a catalog interpretation, not a runbook.

Security analyst

Signals on file: no CVSS/EPSS yet. It is not currently listed in the CISA Known Exploited catalog. Weakness classes: CWE-20, CWE-78, CWE-88. Sources contributing to this record: github, osv, pypa. Public exploit references, when present, are outbound links only and are not proof of active exploitation. This is a catalog interpretation of stored metadata.

Exploitation and remediation

  • Exploitation evidence

    Not listed as known exploited in CISA KEV. Not in CISA KEV or VulnCheck KEV.

  • Patch and remediation

    No required-action text is stored yet. Use the vendor or CERT links in Sources for patch availability.

  • Safe detection guidance

    Compare installed versions with the affected ranges below and verify the advisory from the original publisher. This site stores metadata and outbound links only; it does not ship exploit code or proof-of-concept payloads.

Code

The project this record applies to. Exploit listings stay in References.

Timeline

Detection, updates, and resolution for this record.

  1. Oct 16, 2026 · GitHub Advisory Database

    Detected

    The Claude Agent SDK for Python passed the 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 value could inject an 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 untru

  2. Oct 16, 2026 · GitHub Advisory Database

    Fix available

    claude-agent-sdk fixed in 0.2.121

  3. Oct 16, 2026 · GitHub Advisory Database

    Fix available

    claude-agent-sdk fixed in 0.2.121

  4. Oct 16, 2026 · GitHub Advisory Database

    Updated

    The Claude Agent SDK for Python passed the 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 value could inject an 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 untru

Affected

  • PyPI claude-agent-sdk0 → 0.2.121
  • pip claude-agent-sdk< 0.2.121

Sources

References