New research exposes how prompt injection in AI agent frameworks can lead to remote code execution. Learn how these ...

Google says attackers are using AI for zero-day research, malware development, reconnaissance, and access to premium AI tools ...

Microsoft’s Azure-based AI development and deployment platform shines with a strong selection of models and agent types and ...

OX Security confirmed arbitrary command execution on six live platforms and estimates 200,000 MCP servers are exposed. Here's ...

Mistral AI launches Workflows, a Temporal-powered orchestration platform for enterprise AI that automates mission-critical processes across logistics, finance, and customer support with millions of ...

Weekly ThreatsDay Bulletin: supply chain attacks, fake support lures, AI tampering, data leaks, ransomware, and exploited ...

Researchers at Google Threat Intelligence Group (GTIG) say that a zero-day exploit targeting a popular open-source web ...

Amit Navindgi discusses the systematic shift at Zoox from fragmented documentation to an AI-driven ecosystem. He explains how ...

Open source software with more than 1 million monthly downloads was compromised after a threat actor exploited a vulnerability in the developers’ account workflow that gave access to its signing keys ...

The landscape of retail trading has shifted more in the last three years than in the previous thirty. AI-driven systems now ...

The parallel might be stretching it a little, but the overseeing (and indeed building) master control analogy rather suits ...

The post How Escape AI Pentesting Exploited SSRF in LiteLLM appeared first on Escape – Application Security & Offensive Security Blog. At Escape, we routinely test the AI infrastructure that teams ...