AI agents are becoming the next target of social engineering, according to the AI Threat Report 2026 released today by OrcaRouter Security Research.

A new benchmark study found AI agents remain vulnerable to prompt injection attacks as companies increasingly roll out the ...

AI chatbots and assistants are extremely vulnerable to exploitation, particularly prompt injection, according to new research ...

The Copilot vulnerability chain requires three steps, two of which are old-fashioned injections and request forgeries. But ...

The attack relies on hidden prompts in a foreign language.

The controversy over vibe coding reached a new high this week after a developer added hidden instructions to his open source Java testing app to sabotage projects performed by AI coding agents. The ...

At Infosecurity Europe 2026, OWASP’s Ariel Fogel warned that prompt injection remains an “unresolved problem” within ...

Even with Lockdown Mode, ChatGPT could be still vulnerable to prompt injections, but the goal is to reduce the likelihood ...

OpenAI has announced more robust security features for the small set of users who might need them.

Your LLM-based systems are at risk of being attacked to access business data, gain personal advantage, or exploit tools to the same ends. Everything you put in the system prompt is public data.

Security researchers turned the chatbot into a "one-click data exfiltration weapon." The post Microsoft’s Copilot AI Caught ...

Using only natural language instructions, researchers were able to bypass Google Gemini's defenses against malicious prompt injection and create misleading events to leak private Calendar data. 18 ...