PT-2026-102686

Ollama versions 0.14.0 before 0.31.2 contain an incorrect authorization vulnerability in the experimental agent mode Bash tool approval mechanism that fails to properly parse shell syntax. Attackers who can influence model output through prompt injection can execute additional shell commands by...

CVE-2026-77177

The Open GenAI Stack (also known as ogx-ai ) version 2026-06-11 , utilized in the Meta AI backend for WhatsApp and other products, is vulnerable to code execution . The root cause is a lack of sanitization allowing prompt injection using Jinja2 template syntax , which enables server-side expressi...

CVE-2026-102697: Incorrect Authorization

Ollama versions 0.14.0 before 0.31.2 contain an incorrect authorization vulnerability in the experimental agent mode Bash tool approval mechanism that fails to properly parse shell syntax. Attackers who can influence model output through prompt injection can execute additional shell commands by...

Where Do LLMs Decide to Break the Rules? Mechanistic Localization of Prompt Injection Compliance

When a prompt injection attack succeeds, a Large Language Model LLM abandons its assigned system role to comply with an adversarial instruction. While prior work has extensively quantified how often this occurs, we ask a more fundamental question: where inside the network does the model actually...

ToolFence: Fine-Grained Authorization for Secure Tool-Using LLM Agents

Tool-using LLM agents remain vulnerable to indirect prompt injection because trusted instructions and untrusted observations share one context, allowing malicious content to steer consequential input-filtering defenses. Multi-path consensus defenses still leave a high attack success rate because...

CVE-2026-77177: Improper Control of Generation of Code

Open GenAI Stack aka ogx-ai 2026-06-11, as used in the Meta AI backend for WhatsApp and other products, allows code execution because prompt injection with Jinja2 template syntax can be used to achieve server-side expression evaluation without sanitization...

CVE-2026-77177

Open GenAI Stack aka ogx-ai 2026-06-11, as used in the Meta AI backend for WhatsApp and other products, allows code execution because prompt injection with Jinja2 template syntax can be used to achieve server-side expression evaluation without sanitization...

EUVD-2026-89070

Open GenAI Stack aka ogx-ai 2026-06-11, as used in the Meta AI backend for WhatsApp and other products, allows code execution because prompt injection with Jinja2 template syntax can be used to achieve server-side expression evaluation without sanitization...

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...

PT-2026-102670

Open GenAI Stack aka ogx-ai 2026-06-11, as used in the Meta AI backend for WhatsApp and other products, allows code execution because prompt injection with Jinja2 template syntax can be used to achieve server-side expression evaluation without sanitization...

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…...

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...

Self-Evolving Defense: Continual Security Policy Learning for LLM Agents

Large language models LLMs increasingly power agents that access sensitive information, use external tools, and modify software repositories. Although these capabilities offer substantial benefits, they also create security risks such as jailbreaks, prompt injection, and vulnerable code generatio...

Render Before Reading: Visual Rendering As a Prompt Injection Defense

Large language models are vulnerable to prompt injection attacks, where third-party adversarial content can hijack the model's behavior. In this paper, we study the role played by the adversarial data's input modality, and identify a systematic asymmetry: multimodal LLMs are more likely to follow...

Same Bytes, Different Authority: Reserved-Token Representations in Chat-Template Prompt Injection

Prompt injection against LLM agents becomes much stronger when the injected instruction is wrapped in the model's own chat template. A forged template marker such as can reach the model either as a single reserved control token or as a sequence of ordinary subword tokens. The two decode to exactl...

FinRT: Distilling Adaptive Red-Teaming Strategies into Reusable Adversarial Generators in Consumer Finance

In regulated industries like consumer finance, seemingly harmless user queries can exploit large language model vulnerabilities, triggering safety failures and pushing responses dangerously close to policy limits. Existing automated red-teaming methods trade off attack effectiveness against...

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...

CVE-2026-100867

spaceship-prompt through 4.22.5 fails to sanitize control characters from project manifest version fields before rendering them in the zsh prompt. Attackers can embed ANSI/OSC escape sequences in version fields of package manifests to manipulate terminal output, rewrite window titles, or spoof...

CVE-2026-100867 spaceship-prompt through 4.22.5 Terminal Escape Sequence Injection

spaceship-prompt through 4.22.5 fails to sanitize control characters from project manifest version fields before rendering them in the zsh prompt. Attackers can embed ANSI/OSC escape sequences in version fields of package manifests to manipulate terminal output, rewrite window titles, or spoof...

CVE-2026-100867 spaceship-prompt through 4.22.5 Terminal Escape Sequence Injection

spaceship-prompt through 4.22.5 fails to sanitize control characters from project manifest version fields before rendering them in the zsh prompt. Attackers can embed ANSI/OSC escape sequences in version fields of package manifests to manipulate terminal output, rewrite window titles, or spoof...