LangAlpha

The harness for agentic trading. Open-source AI agents that research the market, build the thesis, and trade your own brokerage account within the permissions you set. Try LangAlpha ↗ · Get started · Agentic trading · Harness design · Full-stack architecture · Security English · 简体中文 · 日本語 Why...

CVE-2026-109441

LangAlpha through 2026.09.07 contains an improper isolation vulnerability that places all tenants' sandbox containers on Docker's shared default bridge network with inter-container communication enabled. Authenticated users with code execution in their own sandbox can connect directly to other...

CVE-2026-109440

LangAlpha through 2026.09.07 contains an indirect prompt injection vulnerability that allows remote attackers to execute shell commands or Python by planting instructions in web content retrieved by the agent. Because Bash and ExecuteCode lack an allow-list and human-in-the-loop approval, attacke...

CVE-2026-109441 LangAlpha through 2026.09.07 Cross-Tenant Sandbox Exposure via Shared Docker Bridge

LangAlpha through 2026.09.07 contains an improper isolation vulnerability that places all tenants' sandbox containers on Docker's shared default bridge network with inter-container communication enabled. Authenticated users with code execution in their own sandbox can connect directly to other...

EUVD-2026-104681

LangAlpha through 2026.09.07 contains an improper isolation vulnerability that places all tenants' sandbox containers on Docker's shared default bridge network with inter-container communication enabled. Authenticated users with code execution in their own sandbox can connect directly to other...

CVE-2026-109441 LangAlpha through 2026.09.07 Cross-Tenant Sandbox Exposure via Shared Docker Bridge

LangAlpha through 2026.09.07 contains an improper isolation vulnerability that places all tenants' sandbox containers on Docker's shared default bridge network with inter-container communication enabled. Authenticated users with code execution in their own sandbox can connect directly to other...

CVE-2026-109441 LangAlpha through 2026.09.07 Cross-Tenant Sandbox Exposure via Shared Docker Bridge

LangAlpha through 2026.09.07 contains an improper isolation vulnerability that places all tenants' sandbox containers on Docker's shared default bridge network with inter-container communication enabled. Authenticated users with code execution in their own sandbox can connect directly to other...

CVE-2026-109441

LangAlpha versions through 2026.09.07 contain an improper isolation vulnerability (CWE-653) that places all tenants' sandbox containers on Docker's shared default bridge network with inter-container communication enabled. Authenticated users capable of executing code within their own sandbox can ...

CVE-2026-109440 LangAlpha through 2026.09.07 Indirect Prompt Injection RCE via Bash and ExecuteCode

LangAlpha through 2026.09.07 contains an indirect prompt injection vulnerability that allows remote attackers to execute shell commands or Python by planting instructions in web content retrieved by the agent. Because Bash and ExecuteCode lack an allow-list and human-in-the-loop approval, attacke...

CVE-2026-109440 LangAlpha through 2026.09.07 Indirect Prompt Injection RCE via Bash and ExecuteCode

LangAlpha through 2026.09.07 contains an indirect prompt injection vulnerability that allows remote attackers to execute shell commands or Python by planting instructions in web content retrieved by the agent. Because Bash and ExecuteCode lack an allow-list and human-in-the-loop approval, attacke...

CVE-2026-109440 LangAlpha through 2026.09.07 Indirect Prompt Injection RCE via Bash and ExecuteCode

LangAlpha through 2026.09.07 contains an indirect prompt injection vulnerability that allows remote attackers to execute shell commands or Python by planting instructions in web content retrieved by the agent. Because Bash and ExecuteCode lack an allow-list and human-in-the-loop approval, attacke...

EUVD-2026-104680

LangAlpha through 2026.09.07 contains an indirect prompt injection vulnerability that allows remote attackers to execute shell commands or Python by planting instructions in web content retrieved by the agent. Because Bash and ExecuteCode lack an allow-list and human-in-the-loop approval, attacke...

CVE-2026-109440

LangAlpha versions through 2026.09.07 are susceptible to an indirect prompt injection vulnerability. This flaw allows remote attackers to execute shell commands or Python code by embedding malicious instructions within web content retrieved by the agent. The vulnerability exists because the Bash ...

Ginlix AI LangAlpha security vulnerability

Ginlix AI LangAlpha versions 2026.09.07 and earlier contain a security vulnerability stemming from indirect prompt injection. Due to the absence of allowlists and manual approvals for Bash and ExecuteCode, attackers can insert commands into web pages retrieved by the proxy, thereby executing shel...

PT-2026-117936

LangAlpha through 2026.09.07 contains an improper isolation vulnerability that places all tenants' sandbox containers on Docker's shared default bridge network with inter-container communication enabled. Authenticated users with code execution in their own sandbox can connect directly to other...

PT-2026-117935

Name of the Vulnerable Software and Affected Versions LangAlpha versions prior to 2026.09.07 Description An indirect prompt injection allows remote attackers to execute shell commands or Python by placing instructions within web content retrieved by the agent. This occurs because the Bash and...

Ginlix AI LangAlpha: Permissions, licensing, and access control issues

Ginlix AI LangAlpha versions prior to 2026.09.07 have vulnerabilities related to permission licensing and access control. These vulnerabilities stem from improper isolation, where the sandbox containers of all tenants are placed on the same Docker shared default bridge network, and inter-containe...

LangAlpha v2026.09.01

The harness for agentic trading. Open-source AI agents that research the market, build the thesis, and trade your own brokerage account within the permissions you set. Try LangAlpha ↗ · Get started · Agentic trading · Harness design · Full-stack architecture · Security English · 简体中文 · 日本語 Why...

LangAlpha v2026.08.05

A vibe investing agent harness LangAlpha is built to help interpret financial markets and support investment decisions. English ｜ 简体中文 ｜ 日本語 Getting Started • API Docs • Agent Core • Backend • Web • TUI • Skills • MCP Pin a curated news brief from the dashboard, kick off idea generation, and...

LangAlpha v2026.07.30

A vibe investing agent harness LangAlpha is built to help interpret financial markets and support investment decisions. English ｜ 简体中文 ｜ 日本語 Getting Started • API Docs • Agent Core • Backend • Web • TUI • Skills • MCP Pin a curated news brief from the dashboard, kick off idea generation, and...