Three Flaws in Anthropic MCP Git Server Enable File Access and Code Execution

A set of three security vulnerabilities has been disclosed in mcp-server-git, the official Git Model Context Protocol MCP server maintained by Anthropic, that could be exploited to read or delete arbitrary files and execute code under certain conditions. "These flaws can be exploited through prom...

PINA: Prompt Injection Attack against Navigation Agents

Navigation agents powered by large language models LLMs convert natural language instructions into executable plans and actions. Compared to text-based applications, their security is far more critical: a successful prompt injection attack does not just alter outputs but can directly misguide...

Google Gemini Prompt Injection Flaw Exposed Private Calendar Data via Malicious Invites

Cybersecurity researchers have disclosed details of a security flaw that leverages indirect prompt injection targeting Google Gemini as a way to bypass authorization guardrails and use Google Calendar as a data extraction mechanism. The vulnerability, Miggo Security's Head of Research, Liad...

CVE-2026-22708

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...

“Reprompt” attack lets attackers steal data from Microsoft Copilot

Researchers found a method to steal data which bypasses Microsoft Copilot's built-in safety mechanisms. The attack flow, called Reprompt , abuses how Microsoft Copilot handled URL parameters in order to hijack a user’s existing Copilot Personal session. Copilot is an AI assistant which connects t...

Model Security Is the Wrong Frame – The Real Risk Is Workflow Security

As AI copilots and assistants become embedded in daily work, security teams are still focused on protecting the models themselves. But recent incidents suggest the bigger risk lies elsewhere: in the workflows that surround those models. Two Chrome extensions posing as AI helpers were recently...

Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale

The rise of AI agent frameworks has introduced agent skills, modular packages containing instructions and executable code that dynamically extend agent capabilities. While this architecture enables powerful customization, skills execute with implicit trust and minimal vetting, creating a...

CVE-2026-22708

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...

CVE-2026-22708 Cursor has a Terminal Tool Allowlist Bypass via Environment Variables

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...

CVE-2026-22708

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...

CVE-2026-22708 Cursor has a Terminal Tool Allowlist Bypass via Environment Variables

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...

EUVD-2026-2678

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...

Cursor 安全漏洞

Cursor is a Cursor open source intelligent code editor with deep AI integration. A security vulnerability exists in versions prior to Cursor 2.3 that stems from the fact that in autorun mode, certain shell built-in commands can be executed without being whitelisted and without the need for user...

PT-2026-2918

Name of the Vulnerable Software and Affected Versions Cursor versions prior to 2.3 Description Cursor is a code editor designed for programming with AI. When the Cursor Agent operates in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can be executed without appearing on the...

CVE-2024-58340

LangChain versions up to and including 0.3.1 contain a regular expression denial-of-service ReDoS vulnerability in the MRKLOutputParser.parse method libs/langchain/langchain/agents/mrkl/outputparser.py. The parser applies a backtracking-prone regular expression when extracting tool actions from...

PYSEC-2026-75

LangChain versions up to and including 0.3.1 contain a regular expression denial-of-service ReDoS vulnerability in the MRKLOutputParser.parse method libs/langchain/langchain/agents/mrkl/outputparser.py. The parser applies a backtracking-prone regular expression when extracting tool actions from...

CVE-2024-58340 LangChain <= 0.3.1 MRKLOutputParser ReDoS

LangChain versions up to and including 0.3.1 contain a regular expression denial-of-service ReDoS vulnerability in the MRKLOutputParser.parse method libs/langchain/langchain/agents/mrkl/outputparser.py. The parser applies a backtracking-prone regular expression when extracting tool actions from...

CVE-2024-58340

LangChain

Toward Trustworthy Agentic AI: A Multimodal Framework for Preventing Prompt Injection Attacks

Powerful autonomous systems, which reason, plan, and converse using and between numerous tools and agents, are made possible by Large Language Models LLMs, Vision-Language Models VLMs, and new agentic AI systems, like LangChain and GraphChain. Nevertheless, this agentic environment increases the...

Critical LangChain Core Vulnerability Exposes Secrets via Serialization Injection

A critical security flaw has been disclosed in LangChain Core that could be exploited by an attacker to steal sensitive secrets and even influence large language model LLM responses through prompt injection. LangChain Core i.e., langchain-core is a core Python package that's part of the LangChain...