CVE-2025-10015 TCC Bypass via Downloader XPC Service in Sparkle

The Sparkle framework includes an XPC service Downloader.xpc, by default this service is private to the application its bundled with. A local unprivileged attacker can register this XPC service globally which will inherit TCC permissions of the application. Lack of validation of connecting client...

PT-2025-37918

Name of the Vulnerable Software and Affected Versions Sparkle versions prior to 2.7.2 Description The Sparkle framework’s Autoupdate tool lacks authentication for connecting clients. This allows a local, unprivileged attacker to request the installation of a crafted malicious PKG file, leading to...

A Systematic Evaluation of Parameter-Efficient Fine-Tuning Methods for the Security of Code LLMs

Code-generating Large Language Models LLMs significantly accelerate software development. However, their frequent generation of insecure code presents serious risks. We present a comprehensive evaluation of seven parameter-efficient fine-tuning PEFT techniques, demonstrating substantial gains in...

Early Approaches to Adversarial Fine-Tuning for Prompt Injection Defense: a 2022 Study of GPT-3 and Contemporary Models

This paper documents early research conducted in 2022 on defending against prompt injection attacks in large language models, providing historical context for the evolution of this critical security domain. This research focuses on two adversarial attacks against Large Language Models LLMs: promp...

Securing AI Agents: Implementing Role-Based Access Control for Industrial Applications

The emergence of Large Language Models LLMs has significantly advanced solutions across various domains, from political science to software development. However, these models are constrained by their training data, which is static and limited to information available up to a specific date...

Arbitrary Code Injection

Overview Affected versions of this package are vulnerable to Arbitrary Code Injection via the gonja template parsing process. An attacker can access arbitrary files on the server by injecting malicious template statements into prompts. Allowing an attacker to insert a statement into a prompt to...

Malware in @listr1/prompt-adapter-inquirer

Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be rotated immediately from a different computer. The package should be removed, but as full control of the computer may have been given to an outsid...

Malicious Package

Overview @listr1/prompt-adapter-inquirer is a malicious package. This package contains malicious code, and its content was removed from the official package manager. While this package might be attempting to impersonate a valid organization, there is no connection between that organization and th...

Claude Code rg vulnerability does not protect against approval prompt bypass

Due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window. Users on standard Claude Code auto-update will...

GHSA-QXFV-FCPC-W36X Claude Code rg vulnerability does not protect against approval prompt bypass

Due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window. Users on standard Claude Code auto-update will...

CVE-2025-58764 Claude Code rg command had Command Injection that allowed bypass of user approval prompt for command execution

Claude Code is an agentic coding tool. Due to an error in command parsing, versions prior to 1.0.105 were vulnerable to a bypass of the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claud...

CVE-2025-58764 Claude Code rg command had Command Injection that allowed bypass of user approval prompt for command execution

Claude Code is an agentic coding tool. Due to an error in command parsing, versions prior to 1.0.105 were vulnerable to a bypass of the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claud...

CVE-2025-58764

Summary for CVE-2025-58764 (Claude Code): A command-parsing error in Claude Code allowed bypassing the confirmation prompt and executing an untrusted command when an attacker can inject untrusted content into a Claude Code context window. This affects versions prior to 1.0.105. Exploitation requi...

PT-2025-37055

Name of the Vulnerable Software and Affected Versions: Claude Code versions prior to 1.0.105 Description: Claude Code is an agentic coding tool. A flaw in command parsing allowed a bypass of the Claude Code confirmation prompt, potentially triggering the execution of untrusted commands...

CVE-2025-58372

Roo Code is an AI-powered autonomous coding agent that lives in users' editors. Versions 3.25.23 and below contain a vulnerability where certain VS Code workspace configuration files .code-workspace are not protected in the same way as the .vscode folder. If the agent was configured to auto-appro...

CVE-2025-58370

Roo Code is an AI-powered autonomous coding agent that lives in users' editors. Versions below 3.26.0 contain a vulnerability in the command parsing logic where the Bash parameter expansion and indirect reference were not handled correctly. If the agent was configured to auto-approve execution of...

Decoding Latent Attack Surfaces in LLMs: Prompt Injection Via HTML in Web Summarization

Large Language Models LLMs are increasingly integrated into web-based systems for content summarization, yet their susceptibility to prompt injection attacks remains a pressing concern. In this study, we explore how non-visible HTML elements such as , aria-label, and alt attributes can be exploit...

EchoLeak: the First Real-World Zero-Click Prompt Injection Exploit in a Production LLM System

Large language model LLM assistants are increasingly integrated into enterprise workflows, raising new security concerns as they bridge internal and external data sources. This paper presents an in-depth case study of EchoLeak CVE-2025-32711, a zero-click prompt injection vulnerability in Microso...

Exploit Tool Invocation Prompt for Tool Behavior Hijacking in LLM-Based Agentic System

LLM-based agentic systems leverage large language models to handle user queries, make decisions, and execute external tools for complex tasks across domains like chatbots, customer service, and software engineering. A critical component of these systems is the Tool Invocation Prompt TIP, which...

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs

Large Language Models LLMs have seen rapid adoption in recent years, with industries increasingly relying on them to maintain a competitive advantage. These models excel at interpreting user instructions and generating human-like responses, leading to their integration across diverse domains,...