ClawShield 1.0.0

ClawShield is a security proxy for AI agents. It scans all inbound and outbound messages for prompt injection, PII leaks, and secrets...

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...

Langflow has Remote Code Execution in CSV Agent

Summary The CSV Agent node in Langflow hardcodes allowdangerouscode=True, which automatically exposes LangChain’s Python REPL tool pythonreplast. As a result, an attacker can execute arbitrary Python and OS commands on the server via prompt injection, leading to full Remote Code Execution RCE...

GHSA-3645-FXCV-HQR4 Langflow has Remote Code Execution in CSV Agent

Summary The CSV Agent node in Langflow hardcodes allowdangerouscode=True, which automatically exposes LangChain’s Python REPL tool pythonreplast. As a result, an attacker can execute arbitrary Python and OS commands on the server via prompt injection, leading to full Remote Code Execution RCE...

EUVD-2026-8819

Langflow has Remote Code Execution in CSV Agent...

CVE-2026-27966

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.8.0, the CSV Agent node in Langflow hardcodes allowdangerouscode=True, which automatically exposes LangChain’s Python REPL tool pythonreplast. As a result, an attacker can execute arbitrary Python an...

Arbitrary Code Injection

Overview lfx is a lfx is a command-line tool for running Langflow workflows. It provides two main commands: serve and run. Affected versions of this package are vulnerable to Arbitrary Code Injection via the allowdangerouscode=True which automatically exposes LangChain’s Python REPL tool...

CVE-2026-27966 Langflow has Remote Code Execution in CSV Agent

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.8.0, the CSV Agent node in Langflow hardcodes allowdangerouscode=True, which automatically exposes LangChain’s Python REPL tool pythonreplast. As a result, an attacker can execute arbitrary Python an...

CVE-2026-27966

Langflow before version 1.8.0 exposes a remote code execution risk through the CSV Agent node by hardcoding allow_dangerous_code=True, which enables Python REPL access (python_repl_ast) via prompt injection. This allows an attacker to execute arbitrary Python/OS commands on the server. The issue ...

CVE-2026-27966

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.8.0, the CSV Agent node in Langflow hardcodes allowdangerouscode=True, which automatically exposes LangChain’s Python REPL tool pythonreplast. As a result, an attacker can execute arbitrary Python an...

CVE-2026-27966 Langflow has Remote Code Execution in CSV Agent

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.8.0, the CSV Agent node in Langflow hardcodes allowdangerouscode=True, which automatically exposes LangChain’s Python REPL tool pythonreplast. As a result, an attacker can execute arbitrary Python an...

Langflow RCE

The CSV Agent node in Langflow hardcodes allowdangerouscode=True, which automatically exposes LangChain's Python REPL tool pythonreplast. As a result, an attacker can execute arbitrary Python and OS commands on the server via prompt injection, leading to full Remote Code Execution RCE. Module...

RoguePilot Flaw in GitHub Codespaces Enabled Copilot to Leak GITHUB_TOKEN

A vulnerability in GitHub Codespaces could have been exploited by bad actors to seize control of repositories by injecting malicious Copilot instructions in a GitHub issue. The artificial intelligence AI-driven vulnerability has been codenamed RoguePilot by Orca Security. It has since been patche...

AdapTools: Adaptive Tool-Based Indirect Prompt Injection Attacks on Agentic LLMs

The integration of external data services e.g., Model Context Protocol, MCP has made large language model-based agents increasingly powerful for complex task execution. However, this advancement introduces critical security vulnerabilities, particularly indirect prompt injection IPI attacks...

Analysis of LLMs against Prompt Injection and Jailbreak Attacks

Large Language Models LLMs are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient tool for resource-scarce organizations to adopt LLMs for their own purposes. At the same time, LLMs are vulnerable to prompt-based attacks. Thus,...

OpenClaw < 2026.2.3 Prompt Injection (GHSA-782p-5fr5-7fj8)

The version of the OpenClaw AI assistant installed on the remote host is prior to 2026.2.3. It is, therefore, affected by a prompt injection vulnerability: - When the Slack integration is enabled, channel metadata topic/description can be incorporated into the model's system prompt, allowing...

OpenClaw < 2026.2.15 Multiple Vulnerabilities

The version of the OpenClaw AI assistant installed on the remote host is prior to 2026.2.15. It is, therefore, affected by multiple vulnerabilities, including: - A configuration injection issue in the Docker tool sandbox could allow dangerous Docker options such as bind mounts, host networking, a...

CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents

LLM-based code interpreter agents are increasingly deployed in critical workflows, yet their robustness against risks introduced by their code execution capabilities remains underexplored. Existing benchmarks are limited to static datasets or simulated environments, failing to capture the securit...

Red-Teaming Claude Opus and ChatGPT-Based Security Advisors for Trusted Execution Environments

Trusted Execution Environments TEEs e.g., Intel SGX and ArmTrustZone aim to protect sensitive computation from a compromised operating system, yet real deployments remain vulnerable to microarchitectural leakage, side-channel attacks, and fault injection. In parallel, security teams increasingly...

CVE-2026-27001

OpenClaw is a personal AI assistant. Prior to version 2026.2.15, OpenClaw embedded the current working directory workspace path into the agent system prompt without sanitization. If an attacker can cause OpenClaw to run inside a directory whose name contains control/format characters for example...