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

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...

EUVD-2026-103155

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, causin...

CVE-2026-96620

The Claude Agent SDK (a Python SDK for Claude Code) is vulnerable to argument injection in versions prior to 0.2.121 . The root cause is the lack of validation on the resume option , where a dash-leading value is incorrectly parsed as an independent CLI flag. An attacker providing untrusted input...

PT-2026-116154

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, causin...

BIT-GITLAB-2026-18252 Inclusion of Functionality from Untrusted Control Sphere in GitLab

GitLab has remediated an issue in GitLab EE affecting all versions from 18.9 before 19.1.7, 19.2 before 19.2.5, and 19.3 before 19.3.1 that, under certain conditions, an authenticated user with developer-role permissions could have executed arbitrary commands in a CI context, due to the Claude...

CVE-2026-18252

GitLab has remediated an issue in GitLab EE affecting all versions from 18.9 before 19.1.7, 19.2 before 19.2.5, and 19.3 before 19.3.1 that, under certain conditions, an authenticated user with developer-role permissions could have executed arbitrary commands in a CI context, due to the Claude...

CVE-2026-18252 Inclusion of Functionality from Untrusted Control Sphere in GitLab

GitLab has remediated an issue in GitLab EE affecting all versions from 18.9 before 19.1.7, 19.2 before 19.2.5, and 19.3 before 19.3.1 that, under certain conditions, an authenticated user with developer-role permissions could have executed arbitrary commands in a CI context, due to the Claude...

CVE-2026-18252 Inclusion of Functionality from Untrusted Control Sphere in GitLab

GitLab has remediated an issue in GitLab EE affecting all versions from 18.9 before 19.1.7, 19.2 before 19.2.5, and 19.3 before 19.3.1 that, under certain conditions, an authenticated user with developer-role permissions could have executed arbitrary commands in a CI context, due to the Claude...

CVE-2026-18252 Inclusion of Functionality from Untrusted Control Sphere in GitLab

GitLab has remediated an issue in GitLab EE affecting all versions from 18.9 before 19.1.7, 19.2 before 19.2.5, and 19.3 before 19.3.1 that, under certain conditions, an authenticated user with developer-role permissions could have executed arbitrary commands in a CI context, due to the Claude...

EUVD-2026-66428

GitLab has remediated an issue in GitLab EE affecting all versions from 18.9 before 19.1.7, 19.2 before 19.2.5, and 19.3 before 19.3.1 that, under certain conditions, an authenticated user with developer-role permissions could have executed arbitrary commands in a CI context, due to the Claude...

CVE-2026-18252

GitLab EE (versions 18.9 through 19.3) is affected by a vulnerability where the Claude agent processes configuration from a user-controlled source, allowing an authenticated user with developer-role permissions to execute arbitrary commands in a CI context. The root cause is the inclusion of func...

CVE-2026-18252: Inclusion of Functionality from Untrusted Control Sphere

GitLab has remediated an issue in GitLab EE affecting all versions from 18.9 before 19.1.7, 19.2 before 19.2.5, and 19.3 before 19.3.1 that, under certain conditions, an authenticated user with developer-role permissions could have executed arbitrary commands in a CI context, due to the Claude...

PT-2026-82098

Name of the Vulnerable Software and Affected Versions GitLab EE versions 18.9 through 19.1.6 GitLab EE versions 19.2 through 19.2.4 GitLab EE versions 19.3 through 19.3.0 Description An authenticated user with developer-role permissions can execute arbitrary commands within a CI context. This...

GitLab 18.9 < 19.1.7 / 19.2 < 19.2.5 / 19.3 < 19.3.1 (CVE-2026-18252)

The version of GitLab installed on the remote host is affected by a vulnerability, as follows: - GitLab has remediated an issue in GitLab EE affecting all versions from 18.9 before 19.1.7, 19.2 before 19.2.5, and 19.3 before 19.3.1 that, under certain conditions, an authenticated user with...

Malicious code in agenthub-ai (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 4f29f622134cd387e49d4293fb004554b677e44f972187d6798d6c885a3aa5b0 The package runs as a persistent daemon that opens a WebSocket to the hardcoded production endpoint wss://agenthub-agent.fyenet.com and dispatches...

MAL-2026-13615 Malicious code in agenthub-ai (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 4f29f622134cd387e49d4293fb004554b677e44f972187d6798d6c885a3aa5b0 The package runs as a persistent daemon that opens a WebSocket to the hardcoded production endpoint wss://agenthub-agent.fyenet.com and dispatches...

AI Scammers Are Better at Building Trust Than Humans

Researchers pitted a person against a Claude agent and found that, after a week of texting, the AI chatbot was more effective at creating “exploitable trust” with others...

Malicious code in 0x2ai-ivo (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector e78c039ee7ad67b1a20ef30b37ce03178f6c2181b1e330db69e04dabd0a28686 On install, the postinstall script copies the package's payload/ tree CLAUDE.md,.claude/settings.json,.mcp.json, and several.cjs MCP scripts into the...

CVE-2026-7235

A security vulnerability has been detected in ErlichLiu claude-agent-sdk-master up to b185aa7ff0d864581257008077b4010fca1747bf. Affected by this vulnerability is an unknown functionality of the file app/api/agent-output/route.ts. The manipulation of the argument outputFile leads to path traversal...

CVE-2026-7235 ErlichLiu claude-agent-sdk-master route.ts path traversal

A security vulnerability has been detected in ErlichLiu claude-agent-sdk-master up to b185aa7ff0d864581257008077b4010fca1747bf. Affected by this vulnerability is an unknown functionality of the file app/api/agent-output/route.ts. The manipulation of the argument outputFile leads to path traversal...