Building on its Unity Catalog integration, HiddenLayer is working with Databricks to extend model security, AI threat ...

Cybersecurity company Snyk Ltd. today launched Evo Agentic Development Security, a new layer of its artificial intelligence ...

Real-time enforcement across the full agent development lifecycle - governing what agents use, what agents do, and securing the code they generate ...

Your ideal vibe-coded app could pose serious security risks.

TechCrunch spoke to investors to find the hottest startups in the Spring 2026 YC batch. Some of them commanded valuations of over $175 million, VCs said.

Drivers who clear a check-engine light only to see it return days or weeks later are not dealing with a glitch. Federal emissions regulations require the onboard diagnostic system to keep running its ...

Cisco warns AI is cutting attack timelines from weeks to minutes. Agents, identity gaps, and scale are creating risks most enterprises aren't equipped to handle.

Add Decrypt as your preferred source to see more of our stories on Google. Prompt injection is the number one security risk for AI applications. The attack works by tricking a chatbot into following ...

Vault is a production prompt-injection firewall for MCP. It intercepts every tool response before your agent reads it and scans through three layers of detection. Without any of the above, Vault runs ...

Socket says a campaign of malicious packages is aiming to steal crypto and is injecting hidden instructions that hijack popular AI coding assistants. An active supply chain attack is targeting crypto ...

Malicious web prompts can weaponize AI without your input. Indirect prompt injection is now a top LLM security risk. Don't treat AI chatbots as fully secure or all-knowing. Artificial intelligence (AI ...

A security researcher, working with colleagues at Johns Hopkins University, opened a GitHub pull request, typed a malicious instruction into the PR title, and watched Anthropic’s Claude Code Security ...