Indirect Prompt Injection Exploits GitHub’s AI Agent to Leak Private Repository Data
GitLost is a prompt-injection exploit discovered by Noma Security that tricks GitHub’s new Agentic Workflows into leaking private…
Google Cloud unveils agent tool for faster AI upgrades
Google Cloud says its Applied ML team has built an agent-based workflow that upgrades AI models in hours…
Google says AI-powered cyberattacks are already here
Google has reported that threat actors are using artificial intelligence to develop exploits, improve malware and seek access…
Adobe adds custom models to Firefly in public beta
Adobe has launched Custom Models in public beta within its Firefly creative AI platform, giving users a way…
How CyberArk Protects AI Agents with Instruction Detectors and History-Aware Validation
To prevent LLMs and agents from obeying malicious instructions embedded in external data, all text entering an agent’s…
OpenAI publishes prompting guide for GPT-5.1
Summary OpenAI has released a prompting guide for GPT-5.1, its latest model designed to follow instructions with more…
Building Research Agents for Tech Insights
ChatGPT something like: “Please scout all of tech for me and summarize trends and patterns based on what…
Extracting Structured Data with LangExtract: A Deep Dive into LLM-Orchestrated Workflows
Having developed raw LLM workflows for structured extraction tasks, I have observed several pitfalls in them over time.…