Hackers can hijack ChatGPT, Claude, and Gemini with nothing but a sentence. OpenAI says the problem may never be fully solved.

Ghost CMS SQL injection campaign has compromised 700+ websites — including Harvard University, Oxford University, and DuckDuckGo — using a CVSS 9.4 flaw to inject ClickFix malware lures that trick ...

AI agents have fundamentally changed the threat model of AI model-based applications. By equipping these models with plugins (also called tools), your agents no longer just generate text; they now ...

LangChain and LangGraph patch three high-severity flaws exposing files, secrets, and conversation histories Vulnerabilities included path traversal, deserialization leaks, and SQL injection in SQLite ...

DuckDB Spec-OS for multi-org AI agent swarms. Central specification management, 280+ SQL macros, interactive agent REPL, MCP Apps, meta-learning, and smart extensions. src/agent_farm/ ├── cli.py # ...

Last month we released Julius, a tool that answers the question: “what LLM service is running on this endpoint?” Julius identifies the infrastructure. But identification is only the first step. The ...

Multiple Fortinet FortiWeb instances recently infected with web shells are believed to have been compromised using public exploits for a recently patched remote code execution (RCE) flaw tracked as ...

Anthropic says it won't fix an SQL injection vulnerability in its SQLite Model Context Protocol (MCP) server that a researcher says could be used to hijack a support bot and prompt the AI agent to ...

PandasAI, an open source project by SinaptikAI, has been found vulnerable to Prompt Injection attacks. An attacker with access to the chat prompt can craft malicious input that is interpreted as code, ...