CVE-2026-2256-PoC

CVE-2026–2256 PoC 执行摘要 在 MS-Agent 框架 1.5.2 版本的 Shell 工具组件中发现了一个严重的命令注入漏洞（CVE-2026–2256，CVSS X.X）。该漏洞源于对用户影响的输入未进行适当的清理，这些输入被直接传递到 shell 执行上下文中，从而能够执行非预期的命令。 攻击者可以通过将精心构造的内容注入到代理所消费的数据源（如提示词、文档、日志或研究输入）中来利用此漏洞，无需直接访问 shell 或明确滥用操作员权限。因此，在代理的正常执行流程中，任意命令都可以以 MS-Agent 进程在主机系统上的权限执行，可能导致主机完全被攻陷。...

Improper Neutralization of Input Used for LLM Prompting

Overview strands-agents-tools is an A collection of specialized tools for Strands Agents Affected versions of this package are vulnerable to Improper Neutralization of Input Used for LLM Prompting via the shell tool. An attacker can execute arbitrary operating system commands by crafting a prompt...

CVE-2026-18733

CVE-2026-18733 affects the Shell tool in Amazon Strands Agents Tools prior to v0.8.0. A crafted prompt can set non_interactive to true, bypassing the consent gate and potentially allowing remote execution of arbitrary OS commands on the agent host. Impact appears to involve remote command executi...

CVE-2026-18733 Prompt injection bypasses shell tool consent gate in Strands Agents Tools

A prompt injection vulnerability in the shell tool in Amazon Strands Agents Tools before 0.8.0 might allow remote actors to execute arbitrary operating system commands on the agent's host via a crafted prompt that sets the noninteractive parameter to true, bypassing the human consent gate. To...

CVE-2026-18733

A prompt injection vulnerability in the shell tool in Amazon Strands Agents Tools before 0.8.0 might allow remote actors to execute arbitrary operating system commands on the agent's host via a crafted prompt that sets the noninteractive parameter to true, bypassing the human consent gate. To...

PYSEC-2026-1204 AWorld OS Command Injection vulnerability

A vulnerability was found in inclusionAI AWorld up to 8c257626e648d98d793dd9a1a950c2af4dd84c4e. It has been rated as critical. This issue affects the function subprocess.run/subprocess.Popen of the file AWorld/aworld/virtualenvironments/terminals/shelltool.py. The manipulation leads to os command...

CVE-2026-40153 PraisonAIAgents Affected by Environment Variable Secret Exfiltration via os.path.expandvars() Bypassing shell=False in Shell Tool

PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, the executecommand function in shelltools.py calls os.path.expandvars on every command argument at line 64, manually re-implementing shell-level environment variable expansion despite using shell=False line 88 for security. This...

CVE-2026-40153

PraisonAIAgents is affected by CVE-2026-40153: prior to 1.5.128, execute_command in shell_tools.py expands environment variables via os.path.expandvars() for all command arguments, despite shell=False, enabling exfiltration of secrets (DB credentials, API keys, cloud keys). The approval UI also s...

CVE-2026-40153 PraisonAIAgents Affected by Environment Variable Secret Exfiltration via os.path.expandvars() Bypassing shell=False in Shell Tool

PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, the executecommand function in shelltools.py calls os.path.expandvars on every command argument at line 64, manually re-implementing shell-level environment variable expansion despite using shell=False line 88 for security. This...

EUVD-2026-11486

A weakness has been identified in OpenAkita up to 1.24.3. This impacts the function run of the file src/openakita/tools/shell.py of the component Chat API Endpoint. Executing a manipulation of the argument Message can lead to os command injection. The attack is restricted to local execution. The...

CVE-2026-29783 GitHub Copilot CLI allows for dangerous shell expansion patterns that enable arbitrary command execution

The shell tool within GitHub Copilot CLI versions prior to and including 0.0.422 can allow arbitrary code execution through crafted bash parameter expansion patterns. An attacker who can influence the commands executed by the agent e.g., via prompt injection through repository files, MCP server...

MS-Agent does not properly sanitize commands sent to its shell tool, allowing for RCE

Overview A command injection vulnerability was identified in the MS-Agent framework that can be triggered through unsanitized prompt-derived input. An attacker can craft untrusted input introduced via a chat prompt or other external content sources, resulting in arbitrary command execution on the...

PYSEC-2026-2309

Weblate is a web based localization tool. Prior to 5.16.0, the SSH management console did not validate the passed input while adding the SSH host key, which could lead to an argument injection to ssh-add. Version 5.16.0 fixes the issue. As a workaround, properly limit access to the management...

Exploit for CVE-2026-2256

CVE-2026–2256 PoC Executive Summary A critical command in...

Arbitrary Command Injection

Overview aworld is an Ant Agent Package Affected versions of this package are vulnerable to Arbitrary Command Injection through the subprocess.run and subprocess.Popen functions in shelltool.py. This allows an attacker to inject malicious commands due to insufficient sanitization of user-supplied...

CVE-2025-4032

A vulnerability was found in inclusionAI AWorld up to 8c257626e648d98d793dd9a1a950c2af4dd84c4e. It has been rated as critical. This issue affects the function subprocess.run/subprocess.Popen of the file AWorld/aworld/virtualenvironments/terminals/shelltool.py. The manipulation leads to os command...

Exploit for Improper Handling of Exceptional Conditions in Apache Struts

StrutsShell Apache Struts CVE-2017-5638 Shell Introducti...

[SECURITY] Fedora 24 Update: parallel-20160222-1.fc24

GNU Parallel is a shell tool for executing jobs in parallel using one or mo re machines. A job is typically a single command or a small script that has to be run for each of the lines in the input. The typical input is a list of file s, a list of hosts, a list of users, or a list of tables. If yo...

Compilation escape the antivirus production methods-vulnerability warning-the black bar safety net

Today I to famous hacking software dove gray VIP2005, for example, said the following What about the use of pseudo-SMC in the art to add a little pseudo-flower instructions to transform your ownfree killTrojan! It says here that the pseudo-SMC mean the use of SMC principles of the transfer code...