GHSA-782P-5FR5-7FJ8 OpenClaw Affected by Remote Code Execution via System Prompt Injection in Slack Channel Descriptions

Summary When the Slack integration is enabled, Slack channel metadata topic/description could be incorporated into the model's system prompt. Impact Prompt injection is a documented risk for LLM-driven systems. This issue increased the injection surface by allowing untrusted Slack channel metadat...

PT-2026-20318

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.2.3 Description OpenClaw is a personal AI assistant. When the Slack integration is enabled, Slack channel metadata topic/description can be incorporated into the model's system prompt. This increases the injecti...

The Librarian does not secure its interface, allowing for access to internal system data

Overview Multiple vulnerabilities were discovered in The Librarian, an AI-powered personal assistant tool provided by the company TheLibrarian.io. The Librarian can be used to manage personal email, calendar, documents, and other information through external services, such as Gmail and Google...

Securing AI Agents against Prompt Injection Attacks

Retrieval-augmented generation RAG systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a comprehensive benchmark for evaluating prompt injection risks in RAG-enabled A...

Mindgard Finds Sora 2 Vulnerability Leaking Hidden System Prompt via Audio

AI security firm Mindgard discovered a flaw in OpenAI's Sora 2 model, forcing the video generator to leak…...

EUVD-2025-34183

A security issue exists within the Rockwell Automation Driver Package x64 Microsoft Installer File MSI repair functionality, installed with FTLinx. Authenticated attackers with valid Windows Users credentials can initiate a repair and hijack the resulting console window for vbpinstall.exe. This...

EUVD-2025-25780

Malicious code in bioql PyPI...

SecInfer: Preventing Prompt Injection Via Inference-Time Scaling

Prompt injection attacks pose a pervasive threat to the security of Large Language Models LLMs. State-of-the-art prevention-based defenses typically rely on fine-tuning an LLM to enhance its security, but they achieve limited effectiveness against strong attacks. In this work, we propose...

CVE-2025-10015

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...

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...

Large Reasoning Models Are Autonomous Jailbreak Agents

Jailbreaking -- bypassing built-in safety mechanisms in AI models -- has traditionally required complex technical procedures or specialized human expertise. In this study, we show that the persuasive capabilities of large reasoning models LRMs simplify and scale jailbreaking, converting it into a...

TelegAI Cross Site Scripting

TelegAI, a web application for constructing and chatting with AI Characters, is vulnerable to persistent cross site scripting vulnerabilities in its chat component and character container component. An attacker can achieve arbitrary client-side script execution by crafting an AI Character with SV...

Exploit for CVE-2025-51860

CVE-2025-51860 Vulnerability description TelegAI, a web...

Exploit for CVE-2025-51859

CVE-2025-51859 Vulnerability description Chaindesk, a w...

PT-2025-23167 · Blackmagic Design · Davinci Resolve

Name of the Vulnerable Software and Affected Versions: DaVinci Resolve versions prior to the fixed version Description: The issue is related to the use of entitlement "com.apple.security.cs.disable-library-validation" and the lack of launch and library load constraints, allowing a local attacker...

Your First Spring AI 1.0 Application

Your First Spring AI 1.0 Application by Dr. Mark Pollack, Christian Tsolov, and Josh Long Hi, Spring fans! Spring AI is live on the Spring Initializr and everywhere fine bytes might be had. Ask your doctor if AI is right for you! It's an amazing time to be a Java and Spring developer. There's nev...

Security Steerability Is All You Need

The adoption of Generative AI GenAI in various applications inevitably comes with expanding the attack surface, combining new security threats along with the traditional ones. Consequently, numerous research and industrial initiatives aim to mitigate these security threats in GenAI by developing...

System Prompt Poisoning: Persistent Attacks on Large Language Models beyond User Injection

Large language models LLMs have gained widespread adoption across diverse applications due to their impressive generative capabilities. Their plug-and-play nature enables both developers and end users to interact with these models through simple prompts. However, as LLMs become more integrated in...

Analyzing DeepSeek’s System Prompt: Jailbreaking Generative AI

DeepSeek, a disruptive new AI model from China, has shaken the market, sparking both excitement and controversy. While it has gained attention for its capabilities, it also raises pressing security concerns. Allegations have surfaced about its training data, with claims that it may have leveraged...

AI Under the Microscope—What’s Changed in the OWASP Top 10 for LLMs 2025

As AI continues to evolve, so do the threats and vulnerabilities that surround Large Language Models LLMs. The OWASP Top 10 for LLM Applications 2025 introduces critical updates that reflect the rapid changes in how these models are applied in real-world scenarios. While the list includes...