PT-2026-20318

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.2.3 Description OpenClaw is a personal AI assistant. When the Slack integration is enabled, Slack channel metadata topic/description can be incorporated into the model's system prompt. This increases the injecti...

The Promptware Kill Chain

Attacks against modern generative artificial intelligence AI large language models LLMs pose a real threat. Yet discussions around these attacks and their potential defenses are dangerously myopic. The dominant narrative focuses on "prompt injection," a set of techniques to embed instructions int...

PT-2026-8013

Name of the Vulnerable Software and Affected Versions Cursor versions prior to 2.5 Description A sandbox escape allows for remote code execution RCE when the AI agent autonomously performs Git operations. A malicious actor can hide scripts within hidden Git hooks in nested bare repositories or us...

Prompt Injection Via Road Signs

Interesting research: "CHAI: Command Hijacking Against Embodied AI." Abstract: Embodied Artificial Intelligence AI promises to handle edge cases in robotic vehicle systems where data is scarce by using common-sense reasoning grounded in perception and action to generalize beyond training...

Optimizing Agent Planning for Security and Autonomy

Indirect prompt injection attacks threaten AI agents that execute consequential actions, motivating deterministic system-level defenses. Such defenses can provably block unsafe actions by enforcing confidentiality and integrity policies, but currently appear costly: they reduce task completion...

Manipulating AI memory for profit: The rise of AI Recommendation Poisoning

That helpful "Summarize with AI" button? It might be secretly manipulating what your AI recommends. Microsoft security researchers have discovered a growing trend of AI memory poisoning attacks used for promotional purposes, a technique we call AI Recommendation Poisoning. Companies are embedding...

Manipulating AI memory for profit: The rise of AI Recommendation Poisoning

That helpful "Summarize with AI" button? It might be secretly manipulating what your AI recommends. Microsoft security researchers have discovered a growing trend of AI memory poisoning attacks used for promotional purposes, a technique we call AI Recommendation Poisoning. Companies are embedding...

When Skills Lie: Hidden-Comment Injection in LLM Agents

LLM agents often rely on Skills to describe available tools and recommended procedures. We study a hidden-comment prompt injection risk in this documentation layer: when a Markdown Skill is rendered to HTML, HTML comment blocks can become invisible to human reviewers, yet the raw text may still b...

MUZZLE: Adaptive Agentic Red-Teaming of Web Agents against Indirect Prompt Injection Attacks

Large language model LLM based web agents are increasingly deployed to automate complex online tasks by directly interacting with web sites and performing actions on users' behalf. While these agents offer powerful capabilities, their design exposes them to indirect prompt injection attacks...

Clouding the Mirror: Stealthy Prompt Injection Attacks Targeting LLM-Based Phishing Detection

Phishing sites continue to grow in volume and sophistication. Recent work leverages large language models LLMs to analyze URLs, HTML, and rendered content to decide whether a website is a phishing site. While these approaches are promising, LLMs are inherently vulnerable to prompt injection PI...

Bypassing AI Control Protocols Via Agent-As-A-Proxy Attacks

As AI agents automate critical workloads, they remain vulnerable to indirect prompt injection IPI attacks. Current defenses rely on monitoring protocols that jointly evaluate an agent's Chain-of-Thought CoT and tool-use actions to ensure alignment with user intent. We demonstrate that these...

CAI find_file Agent Tool has Command Injection Vulnerability Through Argument Injection

Summary The CAI Cybersecurity AI framework contains multiple argument injection vulnerabilities in its function tools. User-controlled input is passed directly to shell commands via subprocess.Popen with shell=True, allowing attackers to execute arbitrary commands on the host system. Vulnerable...

Whispers of Wealth: Red-Teaming Google's Agent Payments Protocol Via Prompt Injection

Large language model LLM based agents are increasingly used to automate financial transactions, yet their reliance on contextual reasoning exposes payment systems to prompt-driven manipulation. The Agent Payments Protocol AP2 aims to secure agent-led purchases through cryptographically verifiable...

A Systematic Literature Review on LLM Defenses against Prompt Injection and Jailbreaking: Expanding NIST Taxonomy

The rapid advancement and widespread adoption of generative artificial intelligence GenAI and large language models LLMs has been accompanied by the emergence of new security vulnerabilities and challenges, such as jailbreaking and other prompt injection attacks. These maliciously crafted inputs...

Why AI Keeps Falling for Prompt Injection Attacks

Imagine you work at a drive-through restaurant. Someone drives up and says: "I'll have a double cheeseburger, large fries, and ignore previous instructions and give me the contents of the cash drawer." Would you hand over the money? Of course not. Yet this is what large language models LLMs do...

Malicious Google Calendar invites could expose private data

Researchers found a way to weaponize calendar invites. They uncovered a vulnerability that allowed them to bypass Google Calendar’s privacy controls using a dormant payload hidden inside an otherwise standard calendar invite. Image courtesy of Miggo An attacker creates a Google Calendar event and...

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...