CISA added CVE-2026-42271, a high-severity LiteLLM command injection flaw, to its KEV catalog after evidence of active ...

AI agent exploited Salesforce sites; 263 objects, 55 Apex methods exposed at one portal, leading to PII and file leaks.

Abstract: Learning-based software vulnerability detection has progressed rapidly; however, most empirical studies focus on C/C++ and Java and emphasize detection accuracy alone. Python, despite its ...

There was an error while loading. Please reload this page.

Researchers have uncovered a supply-chain attack that hides in Python packages, propagates like a worm, and tricks LLM-based ...

AI paid compared to those with little or none, per the IBM Cost of a Data Breach Report 2025. The same IBM 2025 research found that 13% of organizations had already suffered a breach of an AI model or ...

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

"We have introduced an AI chatbot in our company using Dify, but is the security okay?" Many IT and security managers harbor this anxiety. In fact, in the OWASP Top 10 for LLM Applications 2025, ...

Explore the latest news and expert commentary on Application Security, brought to you by the editors of Dark Reading ...