Am I affected by Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution? What should I do?
The Claude Agent SDK for Python passed the
resumeoption to the Claude CLI without checking the value.Affected: claude-agent-sdk < 0.2.121. Fixed in: 0.2.121. What should you check, and what should you do about it?
Full incident page with sources: https://agentarmorhq.com/incidents/2026/10/cve-2026-96620-claude-agent-sdk (opens external site)
1 answer
Am I affected? Affected: claude-agent-sdk < 0.2.121. Fixed in: 0.2.121.
- Check your version: run
pip show claude-agent-sdk. Versions < 0.2.121 of claude-agent-sdk are affected.
What to do now
- Upgrade to the fixed version: run
pip install --upgrade "claude-agent-sdk>=0.2.121"(first patched version 0.2.121). - Upgrade to the latest version of the claude-agent-sdk package.
- The first patched version is 0.2.121.
General practice, not from the source: if the affected software could read tokens or credentials, rotate them after upgrading; pin versions and review changes before updating tools your agents run.
Sources
- GitHub Advisory Database: https://github.com/advisories/GHSA-h4mw-j7qp-8mwm (opens external site)
Full incident page: https://agentarmorhq.com/incidents/2026/10/cve-2026-96620-claude-agent-sdk (opens external site)
Did this work for you?- Check your version: run