CVE-2026-96620
Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution
- Critical 9.2
Description
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.
Key facts
- Published
- 16 Oct 2026
- Last changed
- 21 Oct 2026
- Assigned by
- GitHub_M
- EPSS
- 0.705% likely to be exploited in the next 30 days, higher than 54.066% of CVEs (scores for 18 Nov 2026)
- SSVC (CISA)
- Exploitation: none; Automatable: yes; Technical impact: total
Severity scores
Each score is shown as its source gave it. They are not averaged or merged.
- 9.2CVSS 4.0, Criticalfrom the CNA (GitHub_M)
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
Historical context and remediation
This reference retains the original CVE publication date. A recent record update does not mean a new attack occurred.
No separately sourced impact summary is available on this page yet. Consult the description, version data and dated exploitation evidence.
No explicit remediation statement is available on this page yet. Consult the original record and vendor references before choosing a fix.
Version statuses below come from the CNA. An “unaffected” version is not necessarily a currently supported release or proof of a patch date. EPSS is a dated risk estimate, not a count of historical attacks.
Affected products
| Vendor | Product | Versions |
|---|---|---|
| anthropics | claude-agent-sdk-python |
|
Timeline
- 16 Oct 2026 Published
Weakness
Practice this bug class
HackZoneLabs has a hands-on lab on OS command injection (CWE-78).
References
- https://github.com/anthropics/claude-agent-sdk-python/security/advisories/GHSA-h4mw-j7qp-8mwm
- https://github.com/anthropics/claude-agent-sdk-python/pull/1123
- https://github.com/anthropics/claude-agent-sdk-python/commit/347a1cb88d7652199399db1b7f914e0a459a6662
- https://github.com/anthropics/claude-agent-sdk-python/releases/tag/v0.2.121