CVE-2026-96620
CRITICAL
9,2
Source: [email protected]
Attack Vector: network
Attack Complexity: low
Privileges Required: none
User Interaction: none
Confidentiality: N/A
Integrity: N/A
Availability: N/A
Description
AI Translation Available
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.
EPSS (Exploit Prediction Scoring System)
Trend Analysis
EPSS (Exploit Prediction Scoring System)
Prevede la probabilità di sfruttamento basata su intelligence sulle minacce e sulle caratteristiche della vulnerabilità.
EPSS Score
0,0058
Percentile
0,5th
Updated
EPSS Score Trend (Last 3 Days)
20
Improper Input Validation
StableCommon Consequences
Security Scopes Affected:
Availability
Confidentiality
Integrity
Potential Impacts:
Dos: Crash, Exit, Or Restart
Dos: Resource Consumption (Cpu)
Dos: Resource Consumption (Memory)
Read Memory
Read Files Or Directories
Modify Memory
Execute Unauthorized Code Or Commands
Applicable Platforms
Technologies:
AI/ML
78
Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
StableCommon Consequences
Security Scopes Affected:
Confidentiality
Integrity
Availability
Non-Repudiation
Potential Impacts:
Execute Unauthorized Code Or Commands
Dos: Crash, Exit, Or Restart
Read Files Or Directories
Modify Files Or Directories
Read Application Data
Modify Application Data
Hide Activities
Applicable Platforms
Technologies:
Not Technology-Specific, AI/ML, Web Server
88
Improper Neutralization of Argument Delimiters in a Command ('Argument Injection')
DraftCommon Consequences
Security Scopes Affected:
Confidentiality
Integrity
Availability
Other
Potential Impacts:
Execute Unauthorized Code Or Commands
Alter Execution Logic
Read Application Data
Modify Application Data
Applicable Platforms
Languages:
Not Language-Specific, PHP
https://github.com/anthropics/claude-agent-sdk-python/commit/347a1cb88d76521993…
https://github.com/anthropics/claude-agent-sdk-python/pull/1123
https://github.com/anthropics/claude-agent-sdk-python/releases/tag/v0.2.121
https://github.com/anthropics/claude-agent-sdk-python/security/advisories/GHSA-…