monty

Monty 一个用 Rust 编写的、供 AI 使用的最小化、安全的 Python 解释器。 实验性 - 该项目仍处于开发阶段，尚未做好正式发布的准备。 一个用 Rust 编写的、供 AI 使用的最小化、安全的 Python 解释器。 Monty 避免了为运行 LLM 生成的代码而使用基于完整容器的沙箱所带来的成本、延迟、复杂性以及各种麻烦。 相反，它让你安全地运行由嵌入在智能体中的 LLM 编写的 Python 代码，启动时间以个位数微秒计算，而不是数百毫秒。 Monty 可以 做什么： 运行一个合理的 Python 子集——足以让你的智能体表达它想要做的事情...

ai-tool-poisoning-guard

ai-tool-poisoning-guard Minimum security-baseline rule for Claude Code, Codex, and Cursor. This free rule closes a real gap in each tool's built-in review. Full ruleset + implementation guide: Gumroad link — coming soon. Your AI coding assistant reviews code. It doesn't review the sentence that...

Securekit

Securekit Securekit protege lo que tus modelos ejecutan—en cualquier sistema de IA. Securekit es un núcleo de seguridad agnóstico de protocolo para la ejecución de herramientas de IA. Se sitúa entre cualquier sistema LLM o de agentes y las herramientas que utilizan, imponiendo ejecución de...

r2d2

r2d2 Plugin de GPT-4 para radare2 Introducción Este es un plugin de radare2 que utiliza GPT-4 para que GPT-4 emita comandos r2 e interprete la salida. https://github.com/dnakov/r2d2/assets/3777433/4bc7b211-bccc-4b04-9350-6bfca8989edb...

BIT-GITLAB-2026-92529 Incorrect Authorization in GitLab

GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.2.7, 19.3 before 19.3.3, and 19.4 before 19.4.1 that under certain conditions could have allowed an authenticated user with developer-role permissions to bypass admin-configured AI tool governance controls for...

PT-2026-102736

GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.2.7, 19.3 before 19.3.3, and 19.4 before 19.4.1 that under certain conditions could have allowed an authenticated user with developer-role permissions to bypass admin-configured AI tool governance controls for...

EUVD-2026-85733

GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.2.7, 19.3 before 19.3.3, and 19.4 before 19.4.1 that under certain conditions could have allowed an authenticated user with developer-role permissions to bypass admin-configured AI tool governance controls for...

CVE-2026-92529

GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.2.7, 19.3 before 19.3.3, and 19.4 before 19.4.1 that under certain conditions could have allowed an authenticated user with developer-role permissions to bypass admin-configured AI tool governance controls for...

CVE-2026-92529: Incorrect Authorization

GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.2.7, 19.3 before 19.3.3, and 19.4 before 19.4.1 that under certain conditions could have allowed an authenticated user with developer-role permissions to bypass admin-configured AI tool governance controls for...

CVE-2026-92529

An improper authorization check in GitLab EE allows an authenticated user with developer-role permissions to bypass admin-configured AI tool governance controls . This vulnerability specifically affects workflows in namespaces that the user does not control. The issue is present in versions 19.1 ...

CVE-2026-92529 Incorrect Authorization in GitLab

GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.2.7, 19.3 before 19.3.3, and 19.4 before 19.4.1 that under certain conditions could have allowed an authenticated user with developer-role permissions to bypass admin-configured AI tool governance controls for...

PT-2026-97618

Name of the Vulnerable Software and Affected Versions GitLab EE versions 19.1 through 19.2.6 GitLab EE versions 19.3 through 19.3.2 GitLab EE versions 19.4 through 19.4.0 Description Improper authorization checks may allow an authenticated user with developer-role permissions to bypass...

The vulnerability of the AI-based tool for automatic analysis of root causes and effective response to incidents in Azure SRE Agent, related to the lack of authentication, allows intruders to elevate their privileges.

The vulnerability of AI-based tools for automatic analysis of root causes and effective response to incidents in Azure SRE operations is related to the lack of authentication. Exploiting this vulnerability can allow attackers, operating remotely, to increase their privileges...

CVE-2026-16204 zevorn rt-claw Telegram-to-AI Tool Execution Flow script.c tool_run_script_execute code injection

A security flaw has been discovered in zevorn rt-claw up to 0.2.0. This affects the function toolrunscriptexecute of the file claw/services/tools/script.c of the component Telegram-to-AI Tool Execution Flow. Performing a manipulation results in code injection. It is possible to initiate the attac...

CVE-2026-16204: Improper Control of Generation of Code

A security flaw has been discovered in zevorn rt-claw up to 0.2.0. This affects the function toolrunscriptexecute of the file claw/services/tools/script.c of the component Telegram-to-AI Tool Execution Flow. Performing a manipulation results in code injection. It is possible to initiate the attac...

Malicious code in leo-config (npm)

The leo-config npm package was compromised as part of the Miasma worm campaign targeting the LeoPlatform npm ecosystem. On June 24, 2026, 20 LeoPlatform packages were published within a 3-second window by a threat actor who had taken over the npm account czirker belonging to the LeoPlatform...

MAL-2026-6421 Malicious code in leo-cli (npm)

The leo-cli npm package was compromised as part of the Miasma worm campaign targeting the LeoPlatform npm ecosystem. On June 24, 2026, 20 LeoPlatform packages were published within a 3-second window by a threat actor who had taken over the npm account czirker belonging to the LeoPlatform...

MAL-2026-6419 Malicious code in leo-cache (npm)

The leo-cache npm package was compromised as part of the Miasma worm campaign targeting the LeoPlatform npm ecosystem. On June 24, 2026, 20 LeoPlatform packages were published within a 3-second window by a threat actor who had taken over the npm account czirker belonging to the LeoPlatform...

MAL-2026-6433 Malicious code in rstreams-shard-util (npm)

The rstreams-shard-util npm package was compromised as part of the Miasma worm campaign targeting the LeoPlatform npm ecosystem. On June 24, 2026, 20 LeoPlatform packages were published within a 3-second window by a threat actor who had taken over the npm account czirker belonging to the...

Malicious code in leo-connector-oracle (npm)

The leo-connector-oracle npm package was compromised as part of the Miasma worm campaign targeting the LeoPlatform npm ecosystem. On June 24, 2026, 20 LeoPlatform packages were published within a 3-second window by a threat actor who had taken over the npm account czirker belonging to the...