CVE-2026-96620: Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution

Should you act?

Critical and remotely reachable

No known exploitation yet, but it is network-reachable without credentials. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.

• No confirmed exploitation. It is not in CISA’s KEV catalog and CISA’s SSVC assessment records no known exploitation. That can change quickly after a public write-up; re-check if you are affected.
• EPSS 0.6%, percentile 47: FIRST’s model estimates a 0.6% chance of exploitation activity in the next 30 days, higher than 47% of all scored CVEs (low). EPSS is a probability, not a verdict.
• Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
• Only applies if your dependency tree includes claude-agent-sdk (PyPI) < 0.2.121, fixed in 0.2.121. Check your lockfile, including transitive dependencies.

What it is

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.

From the GitHub advisory

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.

Weakness type: CWE-20, CWE-78, CWE-88.

Product: claude-agent-sdk (PyPI) · Assigned by: GitHub_M · Published: 2026-10-16

Affected and fixed versions

Severity scores

• Attack vector: network (remotely reachable)
• Attack complexity: low
• Attack requirements: present (depends on deployment conditions)
• Privileges required: none (no login)
• User interaction: none

CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.

Exploitation and urgency

• CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
• CISA SSVC assessment: exploitation none, automatable yes, technical impact total.
• FIRST EPSS (model of 2026-10-21): 0.58% probability of exploitation activity in the next 30 days; percentile 47.

Timeline

• 2026-10-16 — CVE record published by GitHub_M
• 2026-10-16 — GitHub-reviewed advisory GHSA-h4mw-j7qp-8mwm published (critical)
• 2026-10-21 — CVE record last updated

Sources and references

Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.

Vulnerability records

1. GitHub Advisory GHSA-h4mw-j7qp-8mwm github.com
2. CVE.org record CVE-2026-96620 cve.org
3. NVD entry CVE-2026-96620 nvd.nist.gov

Other references from the CVE record and advisory

1. github.com github.com
2. github.com github.com
3. github.com github.com
4. github.com github.com

Critical PyPI advisories · Today’s Security Digest