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

Why it is Amber

• CVSS 9.2 critical
• Remotely exploitable without logging in
• On your watchlist: PyPI

Affected packages

References

• https://github.com/advisories/GHSA-h4mw-j7qp-8mwm
• 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
• https://github.com/advisories/GHSA-h4mw-j7qp-8mwm

Original 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.