Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution
CVE-2026-96620 · GHSA-h4mw-j7qp-8mwm · published 2026-10-16
- Severity
- Critical
- CVSS score
- 9.2
- Chance of exploitation (EPSS)
- 0.70%
- Fixed in
- 0.2.121
- Exploitation No known exploitation
- Automatable Yes
- Technical impact Total
- CISA SSVC
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.
Upgrade claude-agent-sdk to 0.2.121 or later.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| claude-agent-sdk | PyPI | < 0.2.121 | 0.2.121 |
- CriticalUnauthenticated Remote Code Execution in Langflow via Public Flow Build EndpointlangflowExploited
- CriticalRay is vulnerable to Critical RCE via Safari & Firefox Browsers through DNS Rebinding AttackrayExploited
- CriticalLangflow Unauth RCElangflow, langflow-baseExploited
- HighLiteLLM: Authenticated command execution via MCP stdio test endpointslitellmExploited
- CriticalMLflow vulnerable to remote code execution on unauthenticated servers via third-party scorer deserialization importing caller-placed artifacmlflow
- CriticalAgno: Arbitrary code execution via `eval()` on `field_type` in `FunctionCall`agno
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.