ChatGPT Atlas Browser Can Be Tricked by Fake URLs into Executing Hidden Commands

The newly released OpenAI ChatGPT Atlas web browser has been found to be susceptible to a prompt injection attack where its omnibox can be jailbroken by disguising a malicious prompt as a seemingly harmless URL to visit. "The omnibox combined address/search bar interprets input either as a URL to...

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...

Prompt Caching Support in Spring AI with Anthropic Claude

Large language model API costs can accumulate quickly when applications repeatedly send the same prompt content. A typical scenario: you're building a document analyzer that includes a 3,000-token document in every request. Five questions about that document means processing 15,000 tokens of...

Is Your Prompt Poisoning Code? Defect Induction Rates and Security Mitigation Strategies

Large language models LLMs have become indispensable for automated code generation, yet the quality and security of their outputs remain a critical concern. Existing studies predominantly concentrate on adversarial attacks or inherent flaws within the models. However, a more prevalent yet...

The Trojan Example: Jailbreaking LLMs through Template Filling and Unsafety Reasoning

Large Language Models LLMs have advanced rapidly and now encode extensive world knowledge. Despite safety fine-tuning, however, they remain susceptible to adversarial prompts that elicit harmful content. Existing jailbreak techniques fall into two categories: white-box methods e.g., gradient-base...

Improper Input Validation

@anthropic-ai/claude-code is vulnerable to Improper Input Validation. The vulnerability is due to an error in command parsing that allows an attacker to bypass the confirmation prompt and trigger execution of untrusted commands by injecting malicious content into a Claude Code context window...

Prompt injection in Opera Neon: Rapid response through responsible disclosure

Security Prompt injection in Opera Neon: Rapid response through responsible disclosure Share October 23rd, 2025 Hi Opera users, This week, we were able to address a real-world security scenario on Opera Neon thanks to the work of a security researcher team. The researchers reached out to us throu...

CVE-2025-62356

A path traversal vulnerability in all versions of the Qodo Qodo Gen IDE enables a threat actor to read arbitrary local files in and outside of current projects on an end user’s system. The vulnerability can be reached directly and through indirect prompt injection...

CVE-2025-62353

A path traversal vulnerability in all versions of the Windsurf IDE enables a threat actor to read and write arbitrary local files in and outside of current projects on an end user’s system. The vulnerability can be reached directly and through indirect prompt injection...

Agentic AI’s OODA Loop Problem

The OODA loop --for observe, orient, decide, act--is a framework to understand decision-making in adversarial situations. We apply the same framework to artificial intelligence agents, who have to make their decisions with untrustworthy observations and orientation. To solve this problem, we need...

BreakFun: Jailbreaking LLMs Via Schema Exploitation

The proficiency of Large Language Models LLMs in processing structured data and adhering to syntactic rules is a capability that drives their widespread adoption but also makes them paradoxically vulnerable. In this paper, we investigate this vulnerability through BreakFun, a jailbreak methodolog...

EUVD-2025-34890

A path traversal vulnerability in all versions of the Windsurf IDE enables a threat actor to read and write arbitrary local files in and outside of current projects on an end user’s system. The vulnerability can be reached directly and through indirect prompt injection...

CVE-2025-62353

A path traversal vulnerability in all versions of the Windsurf IDE enables a threat actor to read and write arbitrary local files in and outside of current projects on an end user’s system. The vulnerability can be reached directly and through indirect prompt injection...

CVE-2025-62356

A path traversal vulnerability in all versions of the Qodo Qodo Gen IDE enables a threat actor to read arbitrary local files in and outside of current projects on an end user’s system. The vulnerability can be reached directly and through indirect prompt injection...

CVE-2025-62356

A path traversal vulnerability in all versions of the Qodo Qodo Gen IDE enables a threat actor to read arbitrary local files in and outside of current projects on an end user’s system. The vulnerability can be reached directly and through indirect prompt injection...

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-2025-62356

A path traversal vulnerability in all versions of the Qodo Qodo Gen IDE enables a threat actor to read arbitrary local files in and outside of current projects on an end user’s system. The vulnerability can be reached directly and through indirect prompt injection...

CVE-2025-62353

A path traversal vulnerability in all versions of the Windsurf IDE enables a threat actor to read and write arbitrary local files in and outside of current projects on an end user’s system. The vulnerability can be reached directly and through indirect prompt injection...

CVE-2025-62353

A path traversal vulnerability in all versions of the Windsurf IDE enables a threat actor to read and write arbitrary local files in and outside of current projects on an end user’s system. The vulnerability can be reached directly and through indirect prompt injection...

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 ...