From A2A Attacks to Envelope-Layer Defense: Red-Teaming Evaluation of LLM Agents and a Three-Layer Isomorphic Attack-Defense Model

Agent interaction protocols such as ACP and A2A have moved LLM-based agents toward multi-agent collaboration, introducing new security threats. A task sent by a remote peer over A2A is treated as a legitimate request, providing a natural channel for indirect prompt injection. Existing agent...

Pikit: A Composable Toolkit for Indirect Prompt Injection Research and Evaluation

Indirect prompt injection embeds malicious instructions within external content retrieved by LLM-based agents, altering target behavior without user authorization. We introduce pikit, a research toolkit designed to systematically evaluate these threats across three core dimensions: attacks 13...

Fake Email Thread Tricks AI Summarizer Without Hidden Text

Forcepoint X-Labs has published new research showing that indirect prompt injection against AI email summarizers can work without…...

CoDeL: Co-Evolutionary Defense against Indirect Prompt Injection in LLM-Based Agents

Large language model LLM-based agents increasingly rely on external tools and content, exposing them to indirect prompt injection IPI. This threat has motivated a wide range of defenses, among which training-based defenses are often regarded as most reliable. However, existing training-based...

CounterSteer: Suppressing Indirect Prompt Injection with Activation Steering

Indirect prompt injection makes an LLM agent treat untrusted retrieved text as instructions. We present CounterSteer, an inference-time defense that suppresses this behavior inside the model. Per model, a five-step recipe fits a residual-stream direction from paired episodes differing only in...

MetaPermit: Scalable and Auditable Access Control for AI Agents Via LLM-Inferred Meta-Attributes

The rise of autonomous AI agents equipped with tools has introduced significant security risks, ranging from unintended tool misuse to adversarial manipulation through Indirect Prompt Injection IPI attacks. In practice, deployed agent systems such as OpenAI Codex and Claude Code protect tool...

Prompt Injection Detection for Email Agents through Attack Chain Modeling

Large language model email assistants are particularly vulnerable to indirect prompt injection because untrusted email content can be retrieved into the model context and influence subsequent tool use. Existing prompt injection detectors mainly formulate this problem as binary malicious text...

Ajar: Measuring Open Privilege in Agent Defenses

A language model agent acts through the tools it is given. The data it reads while working on a task can redirect what it does with those tools. A growing set of techniques for safe and secure agent execution therefore sits between the agent and its tools, aiming to enforce access control,...

No-Box Vulnerability Analysis: Description-Only Detection of Indirect Prompt Injection Vulnerabilities in MCP Servers

Conventional vulnerability analysis relies on either system access or dynamic interaction, all of which may be unavailable to third-party analysts auditing closed-source, remotely hosted, critical in situ systems, or commercially gated software. Therefore, we propose a new paradigm of no-box...

PT-2026-85580

LaVague 0.2.35 contains a remote code execution vulnerability in PythonFromMarkdownExtractor.extract as object that evaluates untrusted language model output derived from web page content. Attackers can inject malicious Python code through web pages using indirect prompt injection to execute...

CVE-2026-85694: Improper Control of Generation of Code

LaVague 0.2.35 contains a remote code execution vulnerability in PythonFromMarkdownExtractor.extractasobject that evaluates untrusted language model output derived from web page content. Attackers can inject malicious Python code through web pages using indirect prompt injection to execute...

CVE-2026-82217: Improper Limitation of a Pathname to a Restricted Directory

In Eclipse Theia versions 1.73.0 up to but not including 1.75.0, the AI "Agent Mode" file-change tools writeFileContent, suggestFileContent, and the replacement and state helpers resolved a model-supplied file path without a workspace-containment check. A crafted relative path such as ../.bashrc,...

SIR: Self-Improving Red-Teaming for Compute Use Agents

Computer use agents CUAs are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal, and they are increasingly deployed to automate everyday digital tasks. Because they can be exposed to untrusted content while operating, they are...

leash-poc

leash-poc: MCP tool-poisoning, contained by an independent pol...

TraceGrant: A Contract-Governed Security Framework for the Task-Effect Lifecycle of Networked LLM Agents

Networked large language model LLM agents retrieve information from email, cloud storage, calendars, transaction platforms, and Web services to complete multistep tasks that produce persistent external effects. The same content needed for legitimate execution may also contain indirect prompt...

When Agents Go Rogue: The OpenClaw Supply Chain Crisis

When Agents Go Rogue: The OpenClaw Supply Chain Crisis By Aniket Choukde, Vikas Mishra and Yadunadh · August 19, 2026 This blog was also written by Akhil Reddy and Pavan Kumar Podila Executive Summary The cybersecurity landscape is currently undergoing a seismic shift driven by the adoption of...

Workspace Topology As an Attack Vector in Agentic Coding Assistants

Agentic coding assistants are finding widespread use, not just in new code development but in quickly ingesting and leveraging third-party code. This opens up a risk of malicious code being ingested as these coding tools operate with broad filesystem access inside developer workspaces. In this...

EUVD-2026-57929

HCL AION is affected by a vulnerability where indirect prompt injection can lead to HTML injection in rendered output. Injected markup may be displayed to users, potentially resulting in unintended behavior or security impact under certain conditions...

CVE-2026-21832: Undefined Security Weakness

HCL AION is affected by a vulnerability where indirect prompt injection can lead to HTML injection in rendered output. Injected markup may be displayed to users, potentially resulting in unintended behavior or security impact under certain conditions...

Not an A11y: How Android Accessibility Exposes Mobile AI Agents to Indirect Prompt Injection

The rise of autonomous AI agents represents a major paradigm shift in how users interact with mobile devices. Frameworks such as MobileRun and Mobile-Use can autonomously navigate Android applications and execute complex multi-step tasks. To interpret user interfaces, these frameworks rely...