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...

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...

LLM-Enabled Espionage : The AI assistant that moonlights as a mole

Running short on time but still want to stay in the know? Well, we’ve got you covered! We’ve condensed all the key takeaways into a handy audio summary. It began as a low-priority alert from the SOC: an AI assistant accessed an internal finance folder at 2:14 AM. No credentials were stolen. No...

AWS Bedrock Prompt Caching Support in Spring AI

In our previous blog post about Anthropic prompt caching, we explored how prompt caching dramatically reduces API costs and latency by reusing previously processed prompt content. We introduced Spring AI's five strategic caching patterns for Anthropic Claude models and showed how they automatical...

Atlas browser’s Omnibox opens up new privacy and security risks

It seems that with every new agentic browser we discover yet another way to abuse one. OpenAI recently introduced a ChatGPT based AI browser called Atlas. It didn’t take researchers long to find that the combined search and prompt bar—called the Omnibox—can be exploited. By pasting a specially...

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...

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...