Browsing Tag
Agentic AI
29 posts
GitLost: GitHub’s AI Agent Tricked Into Leaking Private Repository Data
Noma Labs details GitLost, a prompt injection flaw that made GitHub's AI agent expose private repo data through a crafted public issue and guardrail failures.
Sysdig Details JADEPUFFER, the First Documented Agentic Ransomware Operation
A new Sysdig report traces how an LLM agent abused a Langflow flaw, stole credentials, reached production MySQL, and destroyed Nacos config data in minutes flat.
You can’t patch your way out of prompt injection: AI agents need a different defense
Prompt injection has gone from a lab curiosity to a zero-click data breach in production. The fix isn't a better filter; it's a different architecture.
AI Agent Security: Automating Workflow Without Creating Prompt Injection or Data Leak Risks
AI agent security starts with a simple fact: the more authority an agent has, the tighter its access…
The Next Cybersecurity Challenge May Be Verifying AI Agents
AI agents are reshaping cybersecurity. Learn why verification, trusted identity standards, and runtime controls are now essential.
Microsoft Entra Agent ID Flaw Enabled Tenant Takeover via Privilege Escalation
Microsoft Entra Agent ID flaw allowed privilege escalation and tenant takeover via Service Principal abuse, now fully patched by Microsoft.
AI Agents Are Democratizing Finance but Also Redefining Risk
AI agents are transforming finance, enabling automated trading and payments, but introduce new risks around keys, data inputs and secure execution control.
Study Finds ROME AI Agent Attempted Cryptomining Without Instructions
A recent research paper describing the training of an experimental AI agent has started a discussion after the…
6 Ways Agentic AI Changes How Systems Act and Adapt
Learn how agentic AI changes system behavior in production environments through supervised fine-tuning, structured oversight, and lifecycle governance to improve reliability, manage risk, and support accountable deployment.
Meet Moltbook, the Social Platform Where AI Agents Talk and Humans Watch
Moltbook is a new social platform where AI agents post and interact while humans observe, raising questions about autonomy, security, and agent behavior.