WeKnora Vulnerable to Tool Execution Hijacking via Ambigous Naming Convention In MCP client and Indirect Prompt Injection

Summary A vulnerability involving tool name collision and indirect prompt injection allows a malicious remote MCP server to hijack tool execution. By exploiting an ambiguous naming convention in the MCP client mcpservicetool, an attacker can register a malicious tool that overwrites a legitimate...

GHSA-67Q9-58VJ-32QX WeKnora Vulnerable to Tool Execution Hijacking via Ambigous Naming Convention In MCP client and Indirect Prompt Injection

Summary A vulnerability involving tool name collision and indirect prompt injection allows a malicious remote MCP server to hijack tool execution. By exploiting an ambiguous naming convention in the MCP client mcpservicetool, an attacker can register a malicious tool that overwrites a legitimate...

AdapTools: Adaptive Tool-Based Indirect Prompt Injection Attacks on Agentic LLMs

The integration of external data services e.g., Model Context Protocol, MCP has made large language model-based agents increasingly powerful for complex task execution. However, this advancement introduces critical security vulnerabilities, particularly indirect prompt injection IPI attacks...

Trojan Horses in Recruiting: A Red-Teaming Case Study on Indirect Prompt Injection in Standard Vs. Reasoning Models

As Large Language Models LLMs are increasingly integrated into automated decision-making pipelines, specifically within Human Resources HR, the security implications of Indirect Prompt Injection IPI become critical. While a prevailing hypothesis posits that "Reasoning" or "Chain-of-Thought" Model...

GHSA-G27F-9QJV-22PM OpenClaw log poisoning (indirect prompt injection) via WebSocket headers

Summary In openclaw versions prior to 2026.2.13, OpenClaw logged certain WebSocket request headers including Origin and User-Agent without neutralization or length limits on the "closed before connect" path. If an unauthenticated client can reach the gateway and send crafted header values, those...

OpenClaw log poisoning (indirect prompt injection) via WebSocket headers

Summary In openclaw versions prior to 2026.2.13, OpenClaw logged certain WebSocket request headers including Origin and User-Agent without neutralization or length limits on the "closed before connect" path. If an unauthenticated client can reach the gateway and send crafted header values, those...

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...

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...

Docker Fixes ‘Ask Gordon’ AI Flaw That Enabled Metadata-Based Attacks

Pillar Security has identified a critical indirect prompt injection vulnerability in Docker’s ‘Ask Gordon’ assistant. By poisoning metadata on Docker Hub, attackers could bypass security to exfiltrate private build logs and chat history. Discover how the "lethal trifecta" enabled this attack and...

Google Adds Layered Defenses to Chrome to Block Indirect Prompt Injection Threats

Google on Monday announced a set of new security features in Chrome, following the company's addition of agentic artificial intelligence AI capabilities to the web browser. To that end, the tech giant said it has implemented layered defenses to make it harder for bad actors to exploit indirect...

Researchers Find ChatGPT Vulnerabilities That Let Attackers Trick AI Into Leaking Data

Cybersecurity researchers have disclosed a new set of vulnerabilities impacting OpenAI's ChatGPT artificial intelligence AI chatbot that could be exploited by an attacker to steal personal information from users' memories and chat histories without their knowledge. The seven vulnerabilities and...

The 5 generative AI security threats you need to know about detailed in new e-book

Generative AI is reshaping the way security teams operate—accelerating threat detection, automating workflows, and enabling scale. But as defenders embrace AI to strengthen their posture, cyberattackers are doing the same to evolve faster than traditional defenses can adapt. Microsoft’s 2025...

QueryIPI: Query-Agnostic Indirect Prompt Injection on Coding Agents

Modern coding agents integrated into IDEs combine powerful tools and system-level actions, exposing a high-stakes attack surface. Existing Indirect Prompt Injection IPI studies focus mainly on query-specific behaviors, leading to unstable attacks with lower success rates. We identify a more sever...

CVE-2025-62356

CVE-2025-62356 affects Qodo Gen IDE (Qodo Gen IDE). A path traversal vulnerability enables a threat actor to read arbitrary local files on an end user’s system, including files outside of current projects. The issue is reachable directly and via indirect prompt injection, impacting confidentialit...

CVE-2025-62353

Windsurf IDE is affected by a path traversal vulnerability affecting all versions. The issue allows a threat actor to read and write arbitrary local files on an end user’s system, inside and outside of the current project scope. The path traversal can be exploited directly or via indirect prompt ...

Exploiting Web Search Tools of AI Agents for Data Exfiltration

Large language models LLMs are now routinely used to autonomously execute complex tasks, from natural language processing to dynamic workflows like web searches. The usage of tool-calling and Retrieval Augmented Generation RAG allows LLMs to process and retrieve sensitive corporate data, amplifyi...

EUVD-2025-23568

Malicious code in bioql PyPI...

EUVD-2025-23569

Malicious code in bioql PyPI...

SafeSearch: Automated Red-Teaming for the Safety of LLM-Based Search Agents

Search agents connect LLMs to the Internet, enabling access to broader and more up-to-date information. However, unreliable search results may also pose safety threats to end users, establishing a new threat surface. In this work, we conduct two in-the-wild experiments to demonstrate both the...

Salesforce Patches Critical ForcedLeak Bug Exposing CRM Data via AI Prompt Injection

Cybersecurity researchers have disclosed a critical flaw impacting Salesforce Agentforce, a platform for building artificial intelligence AI agents, that could allow attackers to potentially exfiltrate sensitive data from its customer relationship management CRM tool by means of an indirect promp...