CVE-2026-96620Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution
- 9.2CriticalCVSS base score
- 0.70%Exploitation in 30 daysEPSS · top 46% of all CVEs
- NoKnown exploitednot in CISA's KEV catalog
- NonePublic exploitsnone known yet
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.
Timeline
ID reserved
By GitHub_M
- 23 days later
· 23 days later
Published
- 5 days later
· 5 days later
Record updated
Changes after publication (a new score, a public exploit, EPSS crossing 1, 10 or 50 %, leaving KEV) are kept since November 2026; earlier ones are not known.
Scores
| Scored by | CVSS | Score | Vector |
|---|---|---|---|
| GitHub_MCNA (assigner) | 4.0 | Critical9.2 | 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 |
| NVDNVD · Awaiting Analysis | 4.0 | Critical9.2 | 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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X |
- EPSS (exploitation in 30 days)
- 0.70% · top 46% of all CVEs (18 Nov 2026)
- CISA SSVC
- Exploitation: none · Automatable: yes · Technical impact: total
The list uses the assigner's score when there is one, then CISA's, then NVD's: Critical 9.2.
Affected products
anthropics · claude-agent-sdk-python
- affected < 0.2.121
Affected packages
From reviewed advisories of the GitHub Advisory Database.
- PyPIclaude-agent-sdkGHSA-h4mw-j7qp-8mwm (opens in a new tab)
References
References4
- https://github.com/anthropics/claude-agent-sdk-python/security/advisories/GHSA-h4mw-j7qp-8mwm (opens in a new tab)x_refsource_CONFIRM
- https://github.com/anthropics/claude-agent-sdk-python/pull/1123 (opens in a new tab)x_refsource_MISC
- https://github.com/anthropics/claude-agent-sdk-python/commit/347a1cb88d7652199399db1b7f914e0a459a6662 (opens in a new tab)x_refsource_MISC
- https://github.com/anthropics/claude-agent-sdk-python/releases/tag/v0.2.121 (opens in a new tab)x_refsource_MISC
Sources
The same CVE in the primary databases and aggregators, to check against.
- CVE.org record (opens in a new tab)
- CVE List JSON (GitHub) (opens in a new tab)
- NVD (opens in a new tab)
- FIRST EPSS (opens in a new tab)
- EUVD EUVD-2026-103155 (opens in a new tab)
- OSV.dev (opens in a new tab)
- GitHub Advisory GHSA-h4mw-j7qp-8mwm (opens in a new tab)
- CIRCL Vulnerability-Lookup (opens in a new tab)
Badge for a README or a ticket
[](https://cveledger.app/cve/CVE-2026-96620)Record last updated .