A one-prompt attack that breaks LLM safety alignment

Large language models LLMs and diffusion models now power a wide range of applications, from document assistance to text-to-image generation, and users increasingly expect these systems to be safety-aligned by default. Yet safety alignment is only as robust as its weakest failure mode. Despite...

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...

Linux Distros Unpatched Vulnerability : CVE-2025-67849

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - A flaw was found in Moodle. This cross-site scripting XSS vulnerability, caused by improper sanitization of AI prompt responses, allows attackers to inject...

CVE-2026-24053

Claude Code is an agentic coding tool. Prior to version 2.0.74, due to a Bash command validation flaw in parsing ZSH clobber syntax, it was possible to bypass directory restrictions and write files outside the current working directory without user permission prompts. Exploiting this required the...

CVE-2026-24887 Claude Code has a Command Injection in find Command Bypasses User Approval Prompt

Claude Code is an agentic coding tool. Prior to version 2.0.72, due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of untrusted commands through the find command. Reliably exploiting this required the ability to add untrusted...

CVE-2026-24887 Claude Code has a Command Injection in find Command Bypasses User Approval Prompt

Claude Code is an agentic coding tool. Prior to version 2.0.72, due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of untrusted commands through the find command. Reliably exploiting this required the ability to add untrusted...

Arbitrary Code Injection

Overview @anthropic-ai/claude-code is an Use Claude, Anthropic's AI assistant, right from your terminal. Claude can understand your codebase, edit files, run terminal commands, and handle entire workflows for you. Affected versions of this package are vulnerable to Arbitrary Code Injection via th...

GHSA-QGQW-H4XQ-7W8W Claude Code has a Command Injection in find Command Bypasses User Approval Prompt

Due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of untrusted commands through the find command. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window. Users on standard Claude...

CVE-2024-4147

In lunary-ai/lunary version 1.2.13, an insufficient granularity of access control vulnerability allows users to delete prompts created in other organizations through ID manipulation. The vulnerability stems from the application's failure to validate the ownership of the prompt before deletion, on...

UBUNTU-CVE-2025-67849

A flaw was found in Moodle. This cross-site scripting XSS vulnerability, caused by improper sanitization of AI prompt responses, allows attackers to inject malicious HTML or script into web pages. When other users view these compromised pages, their sessions could be stolen, or the user interface...

CVE-2025-67849

A flaw was found in Moodle. This cross-site scripting XSS vulnerability, caused by improper sanitization of AI prompt responses, allows attackers to inject malicious HTML or script into web pages. When other users view these compromised pages, their sessions could be stolen, or the user interface...

EUVD-2025-206737

A flaw was found in Moodle. This cross-site scripting XSS vulnerability, caused by improper sanitization of AI prompt responses, allows attackers to inject malicious HTML or script into web pages. When other users view these compromised pages, their sessions could be stolen, or the user interface...

CVE-2025-67849 Moodle: moodle: cross-site scripting (xss) via improper sanitization of ai prompt responses

A flaw was found in Moodle. This cross-site scripting XSS vulnerability, caused by improper sanitization of AI prompt responses, allows attackers to inject malicious HTML or script into web pages. When other users view these compromised pages, their sessions could be stolen, or the user interface...

CVE-2026-24887: Improper Neutralization of Special Elements used in an OS Command

Claude Code is an agentic coding tool. Prior to version 2.0.72, due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of untrusted commands through the find command. Reliably exploiting this required the ability to add untrusted...

CVE-2025-67849: Improper Neutralization of Input During Web Page Generation

A flaw was found in Moodle. This cross-site scripting XSS vulnerability, caused by improper sanitization of AI prompt responses, allows attackers to inject malicious HTML or script into web pages. When other users view these compromised pages, their sessions could be stolen, or the user interface...

CVE-2024-4147

In lunary-ai/lunary version 1.2.13, an insufficient granularity of access control vulnerability allows users to delete prompts created in other organizations through ID manipulation. The vulnerability stems from the application's failure to validate the ownership of the prompt before deletion, on...

EUVD-2024-32706

In lunary-ai/lunary version 1.2.13, an insufficient granularity of access control vulnerability allows users to delete prompts created in other organizations through ID manipulation. The vulnerability stems from the application's failure to validate the ownership of the prompt before deletion, on...

CVE-2024-4147

In lunary-ai/lunary version 1.2.13, an insufficient granularity of access control vulnerability allows users to delete prompts created in other organizations through ID manipulation. The vulnerability stems from the application's failure to validate the ownership of the prompt before deletion, on...