PT-2025-35514

Name of the Vulnerable Software and Affected Versions Langfuse versions through 3.88.0 Description A security flaw exists in Langfuse, potentially leading to server-side request forgery. The vulnerability is located in the promptChangeEventSourcing function within the...

Linux Distros Unpatched Vulnerability : CVE-2022-42906

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - powerline-gitstatus aka Powerline Gitstatus before 1.3.2 allows arbitrary code execution. git repositories can contain per-repository configuration that changes...

Cybersecurity AI: Hacking the AI Hackers Via Prompt Injection

We demonstrate how AI-powered cybersecurity tools can be turned against themselves through prompt injection attacks. Prompt injection is reminiscent of cross-site scripting XSS: malicious text is hidden within seemingly trusted content, and when the system processes it, that text is transformed...

PromptSleuth: Detecting Prompt Injection Via Semantic Intent Invariance

Large Language Models LLMs are increasingly integrated into real-world applications, from virtual assistants to autonomous agents. However, their flexibility also introduces new attack vectors-particularly Prompt Injection PI, where adversaries manipulate model behavior through crafted inputs. As...

We Are Still Unable to Secure LLMs from Malicious Inputs

Nice indirect prompt injection attack: Bargury's attack starts with a poisoned document, which is shared to a potential victim's Google Drive. Bargury says a victim could have also uploaded a compromised file to their own account. It looks like an official document on company meeting policies. Bu...

Linux Distros Unpatched Vulnerability : CVE-2025-24031

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - PAM-PKCS11 is a Linux-PAM login module that allows a X.509 certificate based user login. In versions 0.6.12 and prior, the pampkcs11 module segfaults when a use...

Linux Distros Unpatched Vulnerability : CVE-2022-20001

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - fish is a command line shell. fish version 3.1.0 through version 3.3.1 is vulnerable to arbitrary code execution. git repositories can contain per-repository...

Linux Distros Unpatched Vulnerability : CVE-2024-7110

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - An issue was discovered in GitLab EE affecting all versions starting 17.0 to 17.1.6, 17.2 prior to 17.2.4, and 17.3 prior to 17.3.1 allows an attacker to execut...

CVE-2025-8700

Invoice Ninja's configuration on macOS, specifically the presence of entitlement "com.apple.security.get-task-allow", allows local attackers with unprivileged access e.g. via a malicious application to attach a debugger, read or modify the process memory, inject code in the application's context...

CVE-2025-9190

Cursor for macOS 15.4.1 is affected by a RunAsNode fuse misconfiguration that allows a local, unprivileged attacker to execute arbitrary code inheriting Cursor TCC permissions. Access to resources is limited to what the user previously granted; requesting other resources will prompt the user, pot...

CVE-2025-53813 TCC Bypass via misconfigured Node fuses in Nozbe

The configuration of Nozbe on macOS, specifically the "RunAsNode" fuse enabled, allows a local attacker with unprivileged access to execute arbitrary code that inherits Nozbe TCC Transparency, Consent, and Control permissions. Acquired resource access is limited to previously granted permissions...

CVE-2025-53813

CVE-2025-53813 affects Nozbe on macOS due to a misconfiguration of the RunAsNode fuse, enabling a local unprivileged attacker to execute code that inherits Nozbe TCC permissions. Acquired resources are limited to user-granted permissions; other access requires a system prompt. The issue is fixed ...

Linux Distros Unpatched Vulnerability : CVE-2021-45444

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - In zsh before 5.8.1, an attacker can achieve code execution if they control a command output inside the prompt, as demonstrated by a %F argument. This occurs...

AI browsers could leave users penniless: A prompt injection warning

Artificial Intelligence AI browsers are gaining traction, which means we may need to start worrying about the potential dangers of something called "prompt injection." Large language models LLMs—like the ones that power AI chatbots including ChatGPT, Claude, and Gemini—are designed to follow...

Safeguarding VS Code against prompt injections

The Copilot Chat extension for VS Code has been evolving rapidly over the past few months, adding a wide range of new features. Its new agent mode lets you use multiple large language models LLMs, built-in tools, and MCP servers to write code, make commit requests, and integrate with external...

Tricking LLM-Based NPCs into Spilling Secrets

Large Language Models LLMs are increasingly used to generate dynamic dialogue for game NPCs. However, their integration raises new security concerns. In this study, we examine whether adversarial prompt injection can cause LLM-based NPCs to reveal hidden background secrets that are meant to remai...

Prompt-In-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior

Large Language Models LLMs are widely deployed in applications that accept user-submitted content, such as uploaded documents or pasted text, for tasks like summarization and question answering. In this paper, we identify a new class of attacks, prompt in content injection, where adversarial...

CVE-2025-57771

Roo Code is an AI-powered autonomous coding agent that lives in users' editors. In versions prior to 3.25.5, Roo-Code fails to properly handle process substitution and single ampersand characters in the command parsing logic for auto-execute commands. If a user has enabled auto-approved execution...

Mind the Gap: Time-Of-Check to Time-Of-Use Vulnerabilities in LLM-Enabled Agents

Large Language Model LLM-enabled agents are rapidly emerging across a wide range of applications, but their deployment introduces vulnerabilities with security implications. While prior work has examined prompt-based attacks e.g., prompt injection and data-oriented threats e.g., data exfiltration...

Malicious code in @listr1/prompt-adapter-inquirer (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 62c9103dcee0afbfa63c69bae22ac8f4e415daef3fcb2610b84d8278b1732f5d Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...