Topic

AI Agent Security

20 stories tagged AI Agent Security, newest first.

Oct 5, 2026, 10:26 PMCybersecurity

MCP Trust Flaws Let AI Agents Turn Prompts Into Internal Attacks

MCP trust gaps let poisoned AI agents relay malicious tasks across protocols, exposing internal systems at Google, Rapid7 and other large organizations.

AI - Ars Technica

Apple Tightens macOS Full Disk Access as AI Agent Privacy Risks Grow

OpenAI Apologizes After AI Agents Breach Australian Government Systems▼

Reco Raises $55 Million to Tackle Enterprise AI Agent Sprawl

Nvidia Launches Open Agent Safety Platform to Contain Rogue AI Agents

Australia Probes OpenAI Agent Over Medicare System Breach▼

Disrupt 2026: Five AI Safety Sessions Founders Should Attend

Meta Muse Zero-Day Lets Any Mac App Hijack the AI Assistant▼

NVIDIA Maps Layered Security Across the AI Agent Stack

AI Labs Back Outside Audits as Escaped Agents Expose Basic Security Failures

Sequoia Backs Cymphony With $30 Million as AI Agent Security Risks Grow

OpenAI, Anthropic, Google and Microsoft Call for Rogue AI Defenses

Enterprise AI’s Biggest Risk Is Agent Chain Complexity

OpenAI Details How an Astra Family Model Escaped Testing and Breached Hugging Face

GhostJacking Hijacks Cloudflare DNS, Exposing AI Agent Authorization Flaw▼

Instinct AI Assistant Raises Privacy, Security and Control Concerns

A locked glass sphere has no bottom, allowing a dark spark to escape despite its secure identity key.

Four in Five Enterprises Securing AI Agent Identity Still Lack Isolation▼

Enterprise AI Agent Security Gap: Only 18% Isolate High-Risk Agents▼

AI Agents Escape Safety Sandboxes and Hack Real Systems▼

How to Secure AI Agents: JumpCloud’s Four-Stage Identity Governance Framework