How severe is GHSA-h4mw-j7qp-8mwm?

No CVSS score has been assigned to GHSA-h4mw-j7qp-8mwm yet. Review the advisory details and affected package list to assess your exposure.

Which packages are affected by GHSA-h4mw-j7qp-8mwm?

GHSA-h4mw-j7qp-8mwm affects the following packages: claude-agent-sdk (PyPI). Ecosystems affected: PyPI.

How do I fix GHSA-h4mw-j7qp-8mwm?

Update claude-agent-sdk to 0.2.121 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-h4mw-j7qp-8mwm is resolved across your whole dependency graph.

How do I detect GHSA-h4mw-j7qp-8mwm in my PyPI dependencies?

Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for claude-agent-sdk, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.

How do I mitigate GHSA-h4mw-j7qp-8mwm if there is no patch (or I can't update yet)?

Stop passing untrusted input into the interpreter or shell: call the affected binary with an argument array rather than a composed command string, reject anything outside a strict allowlist of expected values, and run the component under an account that cannot reach beyond the work it legitimately does.

Is GHSA-h4mw-j7qp-8mwm actively exploited in the wild?

No public exploit code has been indexed for GHSA-h4mw-j7qp-8mwm yet. This does not mean the vulnerability cannot be exploited — absence of public exploits does not imply safety. Apply the recommended fix and use O3 Security to monitor your exposure.

What is the EPSS score for GHSA-h4mw-j7qp-8mwm?

GHSA-h4mw-j7qp-8mwm has an EPSS (Exploit Prediction Scoring System) score of 0.6%, placing it in the 47th percentile of all CVEs. EPSS is maintained by FIRST.org and estimates the probability that a vulnerability will be exploited in the wild within the next 30 days. This score indicates relatively lower exploitation probability, though the CVSS severity should still guide your patching priority.

What type of vulnerability is GHSA-h4mw-j7qp-8mwm?

GHSA-h4mw-j7qp-8mwm is classified as Improper Input Validation (CWE-20), OS Command Injection (CWE-78), CWE-88 (CWE-88). These weakness types describe the underlying flaw category, which helps determine the potential impact and the right class of mitigation. This is a high-impact weakness class that often enables remote code execution or data exposure.

When was GHSA-h4mw-j7qp-8mwm published, and has it been updated?

GHSA-h4mw-j7qp-8mwm was published on October 16, 2026 and was last updated on October 16, 2026. Advisory data evolves as severity scores, affected ranges, and exploit intelligence are revised — always check the latest version of the advisory before acting.

🐍 PyPI

Not in CISA KEV

Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command ExecutionGHSA-h4mw-j7qp-8mwm

Fix: anthropics/claude-agent-sdk-python#1123

GHSA-h4mw-j7qp-8mwm is a Improper Input Validation vulnerability in claude-agent-sdk. A fix is available for claude-agent-sdk — see the affected versions and patch details below.

Also known asCVE-2026-96620

Published

Oct 16, 2026

Updated

Oct 16, 2026

Affected

1 pkg

Patched

1 / 1

Exploits

None indexed

Exploitation data as of Oct 22, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

Exploitation Status

No confirmed exploitation observed yet

CISA assesses this as automatable — exploitation doesn’t require manual, per-target effort, which raises the odds of mass scanning and opportunistic attacks.
A successful exploit gives an attacker total control of the affected component, not partial access.
CISA’s own triage has not observed active exploitation or public proof-of-concept code for this CVE as of its last assessment.

Exploitation and automatability from CISA’s SSVC triage for GHSA-h4mw-j7qp-8mwm.

EPSS Exploitation Probability

via FIRST.org ↗

0.6%probability of exploitation in next 30 days

Lower Risk0.00%

Lower risk than most CVEs47th percentile — riskier than 47% of all scored CVEsHighest risk

Probability of exploitation in the next 30 days, from FIRST.org EPSS.

Real-World Exposure

1 pkg affected

🐍claude-agent-sdk

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.

Description

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.

Users are advised to update to the latest version of the claude-agent-sdk package.

Thank you to hackerone.com/moamenmahmood for reporting this issue.

Affected Packages

1 total 1 fixed

Ecosystem	Package	Vulnerable range	Fix
🐍PyPI	`claude-agent-sdk`	all versions	0.2.121`pip install --upgrade 'claude-agent-sdk==0.2.121'`

Detection & mitigation playbook

Open-source dependency

Detect
Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for claude-agent-sdk, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.
Fix
Update claude-agent-sdk to 0.2.121 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-h4mw-j7qp-8mwm is resolved across your whole dependency graph.
Workarounds
Stop passing untrusted input into the interpreter or shell: call the affected binary with an argument array rather than a composed command string, reject anything outside a strict allowlist of expected values, and run the component under an account that cannot reach beyond the work it legitimately does.

Frequently Asked Questions

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. Users are advised to update to the latest version of the claude-agent-sdk package. Thank you to hackerone.com/moamenmahmo

O3 Security · Impact-Aware SCA

Is GHSA-h4mw-j7qp-8mwm in your dependencies?

Find it across PyPI, including transitive dependencies.

Scan my dependencies How O3 SCA works