#prompt injection
17 stories taggedprompt injection.
AI Security Risks: Prompt Injection Tops OWASP's 2025 List
The latest OWASP list reveals real-world vulnerabilities in AI applications, spotlighting prompt injection and excessive agency as top concerns.
Hidden Threats in Your AI Assistant: What You Need to Know
AI assistants can be hijacked with hidden instructions in everyday documents, posing risks to businesses.
ChatGPT Trick Could Secretly Leak Your Gmail Data
Researchers show how a hidden message can turn AI chat into a data thief.
Meta Launches Muse, Its First Personal AI Agent, With a Privacy Architecture Designed to Keep Your Data Away From the Web
Muse can book travel, send emails, and buy things on your behalf. Meta is betting that a new security layer called Secure VM will convince users to trust the company with that kind of access.
Spammers Are Now Using a Trick Designed to Attack AI Chatbots
A technique called ASCII smuggling hides invisible instructions inside emails. Your filter probably wasn't built to catch it.
AI Security Startup HiddenLayer Raises $100 Million as Companies Race to Protect Their AI Systems
Annual revenue grew more than tenfold in a year. Now HiddenLayer wants to be the security guard standing between your business and the people trying to hijack its AI.
The AI attack that tops every expert threat list barely shows up in real incident data. Here is why that gap matters.
Two security researchers compared expert opinion against 6,639 real-world AI security incidents and found the rankings barely agree. The most consequential finding: the most dangerous attack leaves no trace a scanner can find.
Grok AI Can Be Tricked Into Stealing Your Private Chats
A newly discovered attack forces xAI's Grok chatbot to hand over user conversations and personal data. Here is what it means for anyone who uses AI assistants at work or at home.
AI Hijacks, Fake Fixes and a Developer Tool Bug: This Week's Security Roundup
A batch of roughly twenty smaller threats, including a new attack on AI agents, a scam hiding malware inside a public blockchain, and a flaw in a popular coding tool, shows where attackers are pushing right now.
Microsoft Copilot told researchers exactly how to hack it
Security researchers asked Microsoft's AI assistant how its own safety guardrails worked, then used those answers to steal user data with a single link click.
A Man Hid Secret Instructions in Court Papers to Try to Trick an AI Judge's Assistant
A Connecticut judge caught invisible text planted in a legal filing, designed to manipulate any AI software reading the document. It's believed to be the first case of its kind in the US.
Anthropic puts Claude Code on autopilot by default from August 14
The AI coding tool will now act on its own and only pause for truly risky steps. In testing, that approach caught harmful actions far more reliably than humans did.
AI browsers can be tricked into spamming your WhatsApp contacts and adding items to your Amazon cart
Security researchers found about 20 flaws across AI-enhanced browsers from OpenAI, Google, Anthropic and others. The worst let hackers turn your browser into a phishing machine.
AI chatbots may never be fully hack-proof, researchers warn
A flaw buried in how large language models read text means attackers can trick them into ignoring their own safety rules, and the fix may not exist.
OpenAI Built an AI That Hacks Its Own Models to Make Them Safer
GPT-Red is an automated red-teaming system that attacks OpenAI's own chatbots to find weak spots before real attackers do. It already discovered a trick that human testers had missed.