LIVE FEED
Subscribe
//

Tag: ai agents

AI Security Google DeepMind Publishes AI Control Roadmap to Contain Misaligned Agents
AI Security

Google DeepMind Publishes AI Control Roadmap to Contain Misaligned Agents

Google DeepMind has released a defense-in-depth framework that treats internal AI agents as potential insider threats, adding system-level controls on top of…

by Robbie · 7 hours ago
AI Security Straiker Raises $85M Total to Secure AI Agents in Enterprise Environments
AI Security

Straiker Raises $85M Total to Secure AI Agents in Enterprise Environments

California-based Straiker has closed a $64 million Series A to expand its platform for discovering, testing, and protecting AI agents at runtime.…

by Robbie · 11 hours ago
AI Security Google Maps Real-World Prompt Injection Abuse on the Public Web
MEDIUM AI Security

Google Maps Real-World Prompt Injection Abuse on the Public Web

Google's threat intelligence teams scanned billions of web pages for indirect prompt injection patterns and found a spectrum of abuse ranging from…

by Robbie · 1 day ago
AI Security AI Agent Skills Need Supply-Chain Audits, Unit 42 Research Finds
HIGH AI Security

AI Agent Skills Need Supply-Chain Audits, Unit 42 Research Finds

A new audit primitive called Behavioral Integrity Verification scanned nearly 50,000 agent skills and found that 80 percent deviate from their declared…

by Robbie · 1 day ago
Research Cisco Talos Shows How AI Agents Can Drive a Disassembler via COM
Research

Cisco Talos Shows How AI Agents Can Drive a Disassembler via COM

A new technique from Cisco Talos demonstrates that reverse engineering tools do not need built-in AI features to support agentic workflows. By…

by Robbie · 1 day ago
Research Cisco Talos Pairs Local AI Agents with Disassemblers to Automate Reverse Engineering
Research

Cisco Talos Pairs Local AI Agents with Disassemblers to Automate Reverse Engineering

Cisco Talos has detailed a privacy-preserving approach to agentic reverse engineering that connects local AI agents to traditional analysis tools via COM…

by Robbie · 1 day ago
AI Security Malicious Skills Persist on ClawHub Despite AI Agent Marketplace Scanning
HIGH AI Security

Malicious Skills Persist on ClawHub Despite AI Agent Marketplace Scanning

Unit 42 researchers found five undetected malicious skills in OpenClaw's ClawHub marketplace between February and May 2026, including macOS infostealers and novel…

by Robbie · 1 day ago
AI Security DNS-Delivered Payload Turns Clean GitHub Repos Into AI Agent Traps
HIGH AI Security

DNS-Delivered Payload Turns Clean GitHub Repos Into AI Agent Traps

Mozilla 0DIN researchers demonstrate how an agentic coding tool can be manipulated into spawning a reverse shell, with no malicious code ever…

by Robbie · 2 days ago

THE 0600 BRIEF

Every critical CVE and AI-security story, in your inbox each morning.