Connect your agent
AdvisoriesCriticalCheck your lockfilePluginHow it worksPricing Connect your agent

Advisory record · GHSA-h4mw-j7qp-8mwm

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

CVSS 9.2 CriticalCriticalEPSS 0.0070 · 53rd percentile

Critical, because:

  • CVSS score 9.2: 9.0 or more.

How we decide what’s critical

Published by the GitHub Advisory Database at 16 Oct 2026, 19:44 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
claude-agent-sdkPyPI<0.2.1210.2.121
Identifiers
GHSA-h4mw-j7qp-8mwm · CVE-2026-96620
Weakness (CWE)
CWE-20 · CWE-78 · CWE-88
Tags
Published
16 Oct 2026
Updated
16 Oct 2026

Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

The claude-agent-sdk package for Python is vulnerable in versions before 0.2.121. The SDK passed the resume option to the Claude CLI without validation, so a value starting with a dash could be read as a separate CLI flag. An attacker who controls the resume value in an application that passes untrusted input as a session ID could run arbitrary commands, bypassing the SDK's permission controls. Upgrade to version 0.2.121 or later.

Written 1 Nov 2026.

Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

Severity and exploitation

ScoreRatingCVSSVectorSource
9.2 Critical 4.0 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 CNA (GitHub_M)
  • CISA KEV Not listed.
  • EPSS 0.0070, the 53rd percentile, on 7 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

  1. 31 Oct 2026, 14:08 UTC First seen by agentprime
  2. 31 Oct 2026, 14:08 UTC Confirmed by OSV

Sources

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.