VAITP Dataset

← Back to the dataset

CVE-2026-96620

CLI flag injection via unvalidated resume token leads to arbitrary command exec on startup.

  • CVSS 9.2
  • CWE-20
  • Input Validation and Sanitization
  • Remote

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.

CVSS base score
9.2
Published
2026-10-16
OWASP
A03 Injection
Orthogonal defect classification
Interface
Code defect classification
Incorrect Interface
Category
Input Validation and Sanitization
Subcategory
Command Injection
Accessibility scope
Remote
Impact
Arbitrary Code Execution
Affected component
Claude Agent SDK
Fixed by upgrading
Yes

Solution

Upgrade Claude Agent SDK to version 0.2.121 or later.

Vulnerable code sample

import subprocess

def start_claude(session_id: str):
    # VULNERABLE: unvalidated session_id becomes separate CLI flag
    cmd = ["claude", "run", "--resume", session_id]
    subprocess.run(cmd, check=True)

Patched code sample

import subprocess

def start_claude(session_id: str):
    # FIX: reject or sanitize leading dash to prevent flag injection
    if session_id.lstrip().startswith("-"):
        raise ValueError("Invalid session_id")
    cmd = ["claude", "run", "--resume", session_id]
    subprocess.run(cmd, check=True)

Published fix

Public sources link this CVE to the changes below. The code samples above were generated to illustrate the defect; these links lead to the code the project actually changed.

Cite this entry

@misc{vaitp:cve202696620,
  title        = {{CLI flag injection via unvalidated resume token leads to arbitrary command exec on startup.}},
  author       = {Bogaerts, Fr\'ed\'eric and Ivaki, Naghmeh and Fonseca, Jos\'e},
  year         = {2026},
  note         = {VAITP Python Vulnerability Dataset, entry CVE-2026-96620},
  howpublished = {\url{https://netpack.pt/vaitp/vulnerability/CVE-2026-96620/}}
}

Download this entry as JSON Download the whole dataset

Introducing the "VAITP dataset": a specialized repository of Python vulnerabilities and patches, meticulously compiled for the use of the security research community. As Python's prominence grows, understanding and addressing potential security vulnerabilities become crucial. Crafted by and for the cybersecurity community, this dataset offers a valuable resource for researchers, analysts, and developers to analyze and mitigate the security risks associated with Python. Through the comprehensive exploration of vulnerabilities and corresponding patches, the VAITP dataset fosters a safer and more resilient Python ecosystem, encouraging collaborative advancements in programming security.

The supreme art of war is to subdue the enemy without fighting.

Sun Tzu – “The Art of War”

:: Shaping the future through research and ingenuity ::

Before you use the VAITP AI models

Please read and accept the following disclaimer:

By choosing "I understand and accept", you acknowledge that you understand and agree to these terms.