Skip to content
Fencer Intel
critical 9.2

CVE-2026-96620 json

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

published last mo. modified 21d ago also EUVD-2026-103155 , GHSA-h4mw-j7qp-8mwm

cvss
9.2
version 4.0, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.7%
EPSS 0.7% chance of exploitation in 30 days, percentile 53%
public exploits
0
none known

Summary

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.

Patch / fix

  • pypi claude-agent-sdk 0.2.121

Is CVE-2026-96620 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

CISA SSVC

Exploitation
none
Automatable
yes
Technical impact
total
Assessed
21d ago

Exploit prediction

0.71% chance of exploitation in the next 30 days, higher than 53% of all scored CVEs (FIRST EPSS, 2026-11-11).

CVSS scores

assigned by version score vector
CNA 4.0 9.2 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 4.0 9.2 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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Affected packages

ecosystem package affected fixed in
pypi claude-agent-sdk
<0.2.121
0.2.121

Affected products

  • anthropics claude-agent-sdk-python

Classification

Weakness
  • CWE-20 Improper Input Validation
  • CWE-78 Improper Neutralization of Special Elements used in an OS Command
  • CWE-88 Improper Neutralization of Argument Delimiters in a Command

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

The maintainers of anthropics/claude-agent-sdk-python published their own advisory on GitHub. Reviewed sources take precedence over it.